1.CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus ⬇️
We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements. Applications include finding multiple vanishing points in man-made scenes, fitting planes to architectural imagery, or estimating multiple rigid motions within the same sequence. In contrast to previous works, which resorted to hand-crafted search strategies for multiple model detection, we learn the search strategy from data. A neural network conditioned on previously detected models guides a RANSAC estimator to different subsets of all measurements, thereby finding model instances one after another. We train our method supervised as well as self-supervised. For supervised training of the search strategy, we contribute a new dataset for vanishing point estimation. Leveraging this dataset, the proposed algorithm is superior with respect to other robust estimators as well as to designated vanishing point estimation algorithms. For self-supervised learning of the search, we evaluate the proposed algorithm on multi-homography estimation and demonstrate an accuracy that is superior to state-of-the-art methods.
2.Don't Forget The Past: Recurrent Depth Estimation from Monocular Video ⬇️
Autonomous cars need continuously updated depth information. Thus far, the depth is mostly estimated independently for a single frame at a time, even if the method starts from video input. Our method produces a time series of depth maps, which makes it an ideal candidate for online learning approaches. In particular, we put three different types of depth estimation (supervised depth prediction, self-supervised depth prediction, and self-supervised depth completion) into a common framework. We integrate the corresponding networks with a convolutional LSTM such that the spatiotemporal structures of depth across frames can be exploited to yield a more accurate depth estimation. Our method is flexible. It can be applied to monocular videos only or be combined with different types of sparse depth patterns. We carefully study the architecture of the recurrent network and its training strategy. We are first to successfully exploit recurrent networks for real-time self-supervised monocular depth estimation and completion. Extensive experiments show that our recurrent method outperforms its image-based counterpart consistently and significantly in both self-supervised scenarios. It also outperforms previous depth estimation methods of the three popular groups.
3.Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints ⬇️
Creating plausible virtual actors from images of real actors remains one of the key challenges in computer vision and computer graphics. Marker-less human motion estimation and shape modeling from images in the wild bring this challenge to the fore. Although the recent advances on view synthesis and image-to-image translation, currently available formulations are limited to transfer solely style and do not take into account the character's motion and shape, which are by nature intermingled to produce plausible human forms. In this paper, we propose a unifying formulation for transferring appearance and retargeting human motion from monocular videos that regards all these aspects. Our method is composed of four main components and synthesizes new videos of people in a different context where they were initially recorded. Differently from recent appearance transferring methods, our approach takes into account body shape, appearance and motion constraints. The evaluation is performed with several experiments using publicly available real videos containing hard conditions. Our method is able to transfer both human motion and appearance outperforming state-of-the-art methods, while preserving specific features of the motion that must be maintained (e.g., feet touching the floor, hands touching a particular object) and holding the best visual quality and appearance metrics such as Structural Similarity (SSIM) and Learned Perceptual Image Patch Similarity (LPIPS).
4.Deep Learning for Free-Hand Sketch: A Survey ⬇️
Free-hand sketches are highly hieroglyphic and illustrative, which have been widely used by humans to depict objects or stories from ancient times to the present. The recent prevalence of touchscreen devices has made sketch creation a much easier task than ever and consequently made sketch-oriented applications increasingly more popular. The prosperity of deep learning has also immensely promoted the research for the free-hand sketch. This paper presents a comprehensive survey of the free-hand sketch oriented deep learning techniques. The main contents of this survey include: (i) The intrinsic traits and domain-unique challenges of the free-hand sketch are discussed, to clarify the essential differences between free-hand sketch and other data modalities, e.g., natural photo. (ii) The development of the free-hand sketch community in the deep learning era is reviewed, by surveying the existing datasets, research topics, and the state-of-the-art methods via a detailed taxonomy. (iii) Moreover, the bottlenecks, open problems, and potential research directions of this community have also been discussed to promote the future works.
5.Generating Object Stamps ⬇️
We present an algorithm to generate diverse foreground objects and composite them into background images using a GAN architecture. Given an object class, a user-provided bounding box, and a background image, we first use a mask generator to create an object shape, and then use a texture generator to fill the mask such that the texture integrates with the background. By separating the problem of object insertion into these two stages, we show that our model allows us to improve the realism of diverse object generation that also agrees with the provided background image. Our results on the challenging COCO dataset show improved overall quality and diversity compared to state-of-the-art object insertion approaches.
6.An Analysis of Object Representations in Deep Visual Trackers ⬇️
Fully convolutional deep correlation networks are integral components of state-of the-art approaches to single object visual tracking. It is commonly assumed that these networks perform tracking by detection by matching features of the object instance with features of the entire frame. Strong architectural priors and conditioning on the object representation is thought to encourage this tracking strategy. Despite these strong priors, we show that deep trackers often default to tracking by saliency detection - without relying on the object instance representation. Our analysis shows that despite being a useful prior, salience detection can prevent the emergence of more robust tracking strategies in deep networks. This leads us to introduce an auxiliary detection task that encourages more discriminative object representations that improve tracking performance.
7.Fast Neural Network Adaptation via Parameter Remapping and Architecture Search ⬇️
Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as the backbone, commonly pre-trained on ImageNet. However, performance gains can be achieved by designing network architectures specifically for detection and segmentation, as shown by recent neural architecture search (NAS) research for detection and segmentation. One major challenge though, is that ImageNet pre-training of the search space representation (a.k.a. super network) or the searched networks incurs huge computational cost. In this paper, we propose a Fast Neural Network Adaptation (FNA) method, which can adapt both the architecture and parameters of a seed network (e.g. a high performing manually designed backbone) to become a network with different depth, width, or kernels via a Parameter Remapping technique, making it possible to utilize NAS for detection/segmentation tasks a lot more efficiently. In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS. The total computation cost of FNA is significantly less than SOTA segmentation/detection NAS approaches: 1737$\times$ less than DPC, 6.8$\times$ less than Auto-DeepLab and 7.4$\times$ less than DetNAS. The code is available at this https URL.
8.Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks ⬇️
Tables present summarized and structured information to the reader, which makes table structure extraction an important part of document understanding applications. However, table structure identification is a hard problem not only because of the large variation in the table layouts and styles, but also owing to the variations in the page layouts and the noise contamination levels. A lot of research has been done to identify table structure, most of which is based on applying heuristics with the aid of optical character recognition (OCR) to hand pick layout features of the tables. These methods fail to generalize well because of the variations in the table layouts and the errors generated by OCR. In this paper, we have proposed a robust deep learning based approach to extract rows and columns from a detected table in document images with a high precision. In the proposed solution, the table images are first pre-processed and then fed to a bi-directional Recurrent Neural Network with Gated Recurrent Units (GRU) followed by a fully-connected layer with soft max activation. The network scans the images from top-to-bottom as well as left-to-right and classifies each input as either a row-separator or a column-separator. We have benchmarked our system on publicly available UNLV as well as ICDAR 2013 datasets on which it outperformed the state-of-the-art table structure extraction systems by a significant margin.
9.Disentangling Representations using Gaussian Processes in Variational Autoencoders for Video Prediction ⬇️
We introduce MGP-VAE, a variational autoencoder which uses Gaussian processes (GP) to model the latent space distribution. We employ MGP-VAE for the unsupervised learning of video sequences to obtain disentangled representations. Previous work in this area has mainly been confined to separating dynamic information from static content. We improve on previous results by establishing a framework by which multiple features, static or dynamic, can be disentangled. Specifically we use fractional Brownian motions (fBM) and Brownian bridges (BB) to enforce an inter-frame correlation structure in each independent channel. We show that varying this correlation structure enables one to capture different aspects of variation in the data. We demonstrate the quality of our disentangled representations on numerous experiments on three publicly available datasets, and also perform quantitative tests on a video prediction task. In addition, we introduce a novel geodesic loss function which takes into account the curvature of the data manifold to improve learning in the prediction task. Our experiments show quantitatively that the combination of our improved disentangled representations with the novel loss function enable MGP-VAE to outperform the state-of-the-art in video prediction.
10.Training Progressively Binarizing Deep Networks Using FPGAs ⬇️
While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to be desired. Conventional BNN hardware training accelerators perform forward and backward propagations with parameters adopting binary representations, and optimization using parameters adopting floating or fixed-point real-valued representations--requiring two distinct sets of network parameters. In this paper, we propose a hardware-friendly training method that, contrary to conventional methods, progressively binarizes a singular set of fixed-point network parameters, yielding notable reductions in power and resource utilizations. We use the Intel FPGA SDK for OpenCL development environment to train our progressively binarizing DNNs on an OpenVINO FPGA. We benchmark our training approach on both GPUs and FPGAs using CIFAR-10 and compare it to conventional BNNs.
11.Multimodal Semantic Transfer from Text to Image. Fine-Grained Image Classification by Distributional Semantics ⬇️
In the last years, image classification processes like neural networks in the area of art-history and Heritage Informatics have experienced a broad distribution (Lang and Ommer 2018). These methods face several challenges, including the handling of comparatively small amounts of data as well as high-dimensional data in the Digital Humanities. Here, a Convolutional Neural Network (CNN) is used that output is not, as usual, a series of flat text labels but a series of semantically loaded vectors. These vectors result from a Distributional Semantic Model (DSM) which is generated from an in-domain text corpus.
-----
In den letzten Jahren hat die Verwendung von Bildklassifizierungsverfahren wie neuronalen Netzwerken auch im Bereich der historischen Bildwissenschaften und der Heritage Informatics weite Verbreitung gefunden (Lang und Ommer 2018). Diese Verfahren stehen dabei vor einer Reihe von Herausforderungen, darunter dem Umgangmit den vergleichsweise kleinen Datenmengen sowie zugleich hochdimensionalen Da-tenräumen in den digitalen Geisteswissenschaften. Meist bilden diese Methoden dieKlassifizierung auf einen vergleichsweise flachen Raum ab. Dieser flache Zugang verliert im Bemühen um ontologische Eindeutigkeit eine Reihe von relevanten Dimensionen, darunter taxonomische, mereologische und assoziative Beziehungen zwischenden Klassen beziehungsweise dem nicht formalisierten Kontext. Dabei wird ein Convolutional Neural Network (CNN) genutzt, dessen Ausgabe im Trainingsprozess, anders als herkömmlich, nicht auf einer Serie flacher Textlabel beruht, sondern auf einer Serie von Vektoren. Diese Vektoren resultieren aus einem Distributional Semantic Model (DSM), welches aus einem Domäne-Textkorpus generiert wird.
12.Weakly Supervised Visual Semantic Parsing ⬇️
Scene Graph Generation (SGG) aims to extract entities, predicates and their intrinsic structure from images, leading to a deep understanding of visual content, with many potential applications such as visual reasoning and image retrieval. Nevertheless, computer vision is still far from a practical solution for this task. Existing SGG methods require millions of manually annotated bounding boxes for scene graph entities in a large set of images. Moreover, they are computationally inefficient, as they exhaustively process all pairs of object proposals to predict their relationships. In this paper, we address those two limitations by first proposing a generalized formulation of SGG, namely Visual Semantic Parsing, which disentangles entity and predicate prediction, and enables sub-quadratic performance. Then we propose the Visual Semantic Parsing Network, \textsc{VSPNet}, based on a novel three-stage message propagation network, as well as a role-driven attention mechanism to route messages efficiently without a quadratic cost. Finally, we propose the first graph-based weakly supervised learning framework based on a novel graph alignment algorithm, which enables training without bounding box annotations. Through extensive experiments on the Visual Genome dataset, we show \textsc{VSPNet} outperforms weakly supervised baselines significantly and approaches fully supervised performance, while being five times faster.
13.VisionNet: A Drivable-space-based Interactive Motion Prediction Network for Autonomous Driving ⬇️
The comprehension of environmental traffic situation largely ensures the driving safety of autonomous vehicles. Recently, the mission has been investigated by plenty of researches, while it is hard to be well addressed due to the limitation of collective influence in complex scenarios. These approaches model the interactions through the spatial relations between the target obstacle and its neighbors. However, they oversimplify the challenge since the training stage of the interactions lacks effective supervision. As a result, these models are far from promising. More intuitively, we transform the problem into calculating the interaction-aware drivable spaces and propose the CNN-based VisionNet for trajectory prediction. The VisionNet accepts a sequence of motion states, i.e., location, velocity, and acceleration, to estimate the future drivable spaces. The reified interactions significantly increase the interpretation ability of the VisionNet and refine the prediction. To further advance the performance, we propose an interactive loss to guide the generation of the drivable spaces. Experiments on multiple public datasets demonstrate the effectiveness of the proposed VisionNet.
14.Perception and Decision-Making of Autonomous Systems in the Era of Learning: An Overview ⬇️
The ability of inferring its own ego-motion, autonomous understanding the surroundings and planning trajectory are the features of autonomous robot systems. Therefore, in order to improve the perception and decision-making ability of autonomous robot systems, Simultaneous localization and mapping (SLAM) and autonomous trajectory planning are widely researched, especially combining learning-based algorithms.
In this paper, we mainly focus on the application of learning-based approaches to perception and decision-making, and survey the current state-of-the-art SLAM and trajectory planning algorithms. Firstly, we delineate the existing classical SLAM solutions and review deep learning-based methods of environment perception and understanding, including deep learning-based monocular depth estimation, ego-motion prediction, image enhancement, object detection, semantic segmentation and their combinations with previous SLAM frameworks. Secondly, we summarize the existing path planning and trajectory planning methods and survey the navigation methods based on reinforcement learning. Finally, several challenges and promising directions are concluded to related researchers for future work in both autonomous perception and decision-making.
15.Bridging Knowledge Graphs to Generate Scene Graphs ⬇️
Scene graphs are powerful representations that encode images into their abstract semantic elements, i.e, objects and their interactions, which facilitates visual comprehension and explainable reasoning. On the other hand, commonsense knowledge graphs are rich repositories that encode how the world is structured, and how general concepts interact. In this paper, we present a unified formulation of these two constructs, where a scene graph is seen as an image-conditioned instantiation of a commonsense knowledge graph. Based on this new perspective, we re-formulate scene graph generation as the inference of a bridge between the scene and commonsense graphs, where each entity or predicate instance in the scene graph has to be linked to its corresponding entity or predicate class in the commonsense graph. To this end, we propose a heterogeneous graph inference framework allowing to exploit the rich structure within the scene and commonsense at the same time. Through extensive experiments, we show the proposed method achieves significant improvement over the state of the art.
16.SGD with Hardness Weighted Sampling for Distributionally Robust Deep Learning ⬇️
Distributionally Robust Optimization (DRO) has been proposed as an alternative to Empirical Risk Minimization (ERM) in order to account for potential biases in the training data distribution. However, its use in deep learning has been severely restricted due to the relative inefficiency of the optimizers available for DRO in comparison to the wide-spread Stochastic Gradient Descent (SGD) based optimizers for deep learning with ERM. We propose SGD with Hardness weighted sampling, an efficient optimization method for machine learning with DRO with a focus on deep learning. In this work, we propose SGD with hardness weighted sampling, a principled and efficient optimization method for DRO in machine learning that is particularly suited in the context of deep learning. We show that our optimization method can be interpreted as a principled Hard Example Mining strategy. Similar to an online hard example mining strategy in essence and in practice, the proposed algorithm is straightforward to implement and computationally as efficient as SGD-based optimizers used for deep learning. It only requires adding a softmax layer and maintaining a history of the loss values for each training example to compute adaptive sampling probabilities. In contrast to typical ad hoc hard mining approaches, and exploiting recent theoretical results in deep learning optimization, we We also prove the convergence of our DRO algorithm for over-parameterized deep learning networks with ReLU activation and finite number of layers and parameters. Preliminary results demonstrate the feasibility and usefulness of our approach.
17.Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge ⬇️
Purpose: To advance research in the field of machine learning for MR image reconstruction with an open challenge. Methods: We provided participants with a dataset of raw k-space data from 1,594 consecutive clinical exams of the knee. The goal of the challenge was to reconstruct images from these data. In order to strike a balance between realistic data and a shallow learning curve for those not already familiar with MR image reconstruction, we ran multiple tracks for multi-coil and single-coil data. We performed a two-stage evaluation based on quantitative image metrics followed by evaluation by a panel of radiologists. The challenge ran from June to December of 2019. Results: We received a total of 33 challenge submissions. All participants chose to submit results from supervised machine learning approaches. Conclusion: The challenge led to new developments in machine learning for image reconstruction, provided insight into the current state of the art in the field, and highlighted remaining hurdles for clinical adoption.
18.Deep OCT Angiography Image Generation for Motion Artifact Suppression ⬇️
Eye movements, blinking and other motion during the acquisition of optical coherence tomography (OCT) can lead to artifacts, when processed to OCT angiography (OCTA) images. Affected scans emerge as high intensity (white) or missing (black) regions, resulting in lost information. The aim of this research is to fill these gaps using a deep generative model for OCT to OCTA image translation relying on a single intact OCT scan. Therefore, a U-Net is trained to extract the angiographic information from OCT patches. At inference, a detection algorithm finds outlier OCTA scans based on their surroundings, which are then replaced by the trained network. We show that generative models can augment the missing scans. The augmented volumes could then be used for 3-D segmentation or increase the diagnostic value.
19.SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition ⬇️
The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes. In this paper, we propose a generative latent variable model, called SPACE, that provides a unified probabilistic modeling framework that combines the best of spatial-attention and scene-mixture approaches. SPACE can explicitly provide factorized object representations for foreground objects while also decomposing background segments of complex morphology. Previous models are good at either of these, but not both. SPACE also resolves the scalability problems of previous methods by incorporating parallel spatial-attention and thus is applicable to scenes with a large number of objects without performance degradations. We show through experiments on Atari and 3D-Rooms that SPACE achieves the above properties consistently in comparison to SPAIR, IODINE, and GENESIS. Results of our experiments can be found on our project website: this https URL
20.DC-WCNN: A deep cascade of wavelet based convolutional neural networks for MR Image Reconstruction ⬇️
Several variants of Convolutional Neural Networks (CNN) have been developed for Magnetic Resonance (MR) image reconstruction. Among them, U-Net has shown to be the baseline architecture for MR image reconstruction. However, sub-sampling is performed by its pooling layers, causing information loss which in turn leads to blur and missing fine details in the reconstructed image. We propose a modification to the U-Net architecture to recover fine structures. The proposed network is a wavelet packet transform based encoder-decoder CNN with residual learning called CNN. The proposed WCNN has discrete wavelet transform instead of pooling and inverse wavelet transform instead of unpooling layers and residual connections. We also propose a deep cascaded framework (DC-WCNN) which consists of cascades of WCNN and k-space data fidelity units to achieve high quality MR reconstruction. Experimental results show that WCNN and DC-WCNN give promising results in terms of evaluation metrics and better recovery of fine details as compared to other methods.
21.Convolutional Networks with Dense Connectivity ⬇️
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion.Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, encourage feature reuse and substantially improve parameter efficiency. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less parameters and computation to achieve high performance.
22.A context based deep learning approach for unbalanced medical image segmentation ⬇️
Automated medical image segmentation is an important step in many medical procedures. Recently, deep learning networks have been widely used for various medical image segmentation tasks, with U-Net and generative adversarial nets (GANs) being some of the commonly used ones. Foreground-background class imbalance is a common occurrence in medical images, and U-Net has difficulty in handling class imbalance because of its cross entropy (CE) objective function. Similarly, GAN also suffers from class imbalance because the discriminator looks at the entire image to classify it as real or fake. Since the discriminator is essentially a deep learning classifier, it is incapable of correctly identifying minor changes in small structures. To address these issues, we propose a novel context based CE loss function for U-Net, and a novel architecture Seg-GLGAN. The context based CE is a linear combination of CE obtained over the entire image and its region of interest (ROI). In Seg-GLGAN, we introduce a novel context discriminator to which the entire image and its ROI are fed as input, thus enforcing local context. We conduct extensive experiments using two challenging unbalanced datasets: PROMISE12 and ACDC. We observe that segmentation results obtained from our methods give better segmentation metrics as compared to various baseline methods.
23.Hypergraph Spectral Analysis and Processing in 3D Point Cloud ⬇️
Along with increasingly popular virtual reality applications, the three-dimensional (3D) point cloud has become a fundamental data structure to characterize 3D objects and surroundings. To process 3D point clouds efficiently, a suitable model for the underlying structure and outlier noises is always critical. In this work, we propose a hypergraph-based new point cloud model that is amenable to efficient analysis and processing. We introduce tensor-based methods to estimate hypergraph spectrum components and frequency coefficients of point clouds in both ideal and noisy settings. We establish an analytical connection between hypergraph frequencies and structural features. We further evaluate the efficacy of hypergraph spectrum estimation in two common point cloud applications of sampling and denoising for which also we elaborate specific hypergraph filter design and spectral properties. The empirical performance demonstrates the strength of hypergraph signal processing as a tool in 3D point clouds and the underlying properties.
24.Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation ⬇️
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in real-world, due to the domain gap between the artificially synthesized and real LR images. Some efforts are thus taken to capture real-world image pairs. The captured LR-HR image pairs usually suffer from unavoidable misalignment, which hampers the performance of end-to-end learning, however. Here, focusing on the real-world SR, we ask a different question: since misalignment is unavoidable, can we propose a method that does not need LR-HR image pairing and alignment at all and utilize real images as they are? Hence we propose a framework to learn SR from an arbitrary set of unpaired LR and HR images and see how far a step can go in such a realistic and "unsupervised" setting. To do so, we firstly train a degradation generation network to generate realistic LR images and, more importantly, to capture their distribution (i.e., learning to zoom out). Instead of assuming the domain gap has been eliminated, we minimize the discrepancy between the generated data and real data while learning a degradation adaptive SR network (i.e., learning to zoom in). The proposed unpaired method achieves state-of-the-art SR results on real-world images, even in the datasets that favor the paired-learning methods more.
25.What can robotics research learn from computer vision research? ⬇️
The computer vision and robotics research communities are each strong. However progress in computer vision has become turbo-charged in recent years due to big data, GPU computing, novel learning algorithms and a very effective research methodology. By comparison, progress in robotics seems slower. It is true that robotics came later to exploring the potential of learning -- the advantages over the well-established body of knowledge in dynamics, kinematics, planning and control is still being debated, although reinforcement learning seems to offer real potential. However, the rapid development of computer vision compared to robotics cannot be only attributed to the former's adoption of deep learning. In this paper, we argue that the gains in computer vision are due to research methodology -- evaluation under strict constraints versus experiments; bold numbers versus videos.
26.Learning to Move with Affordance Maps ⬇️
The ability to autonomously explore and navigate a physical space is a fundamental requirement for virtually any mobile autonomous agent, from household robotic vacuums to autonomous vehicles. Traditional SLAM-based approaches for exploration and navigation largely focus on leveraging scene geometry, but fail to model dynamic objects (such as other agents) or semantic constraints (such as wet floors or doorways). Learning-based RL agents are an attractive alternative because they can incorporate both semantic and geometric information, but are notoriously sample inefficient, difficult to generalize to novel settings, and are difficult to interpret. In this paper, we combine the best of both worlds with a modular approach that learns a spatial representation of a scene that is trained to be effective when coupled with traditional geometric planners. Specifically, we design an agent that learns to predict a spatial affordance map that elucidates what parts of a scene are navigable through active self-supervised experience gathering. In contrast to most simulation environments that assume a static world, we evaluate our approach in the VizDoom simulator, using large-scale randomly-generated maps containing a variety of dynamic actors and hazards. We show that learned affordance maps can be used to augment traditional approaches for both exploration and navigation, providing significant improvements in performance.
27.Aggressive Perception-Aware Navigation using Deep Optical Flow Dynamics and PixelMPC ⬇️
Recently, vision-based control has gained traction by leveraging the power of machine learning. In this work, we couple a model predictive control (MPC) framework to a visual pipeline. We introduce deep optical flow (DOF) dynamics, which is a combination of optical flow and robot dynamics. Using the DOF dynamics, MPC explicitly incorporates the predicted movement of relevant pixels into the planned trajectory of a robot. Our implementation of DOF is memory-efficient, data-efficient, and computationally cheap so that it can be computed in real-time for use in an MPC framework. The suggested Pixel Model Predictive Control (PixelMPC) algorithm controls the robot to accomplish a high-speed racing task while maintaining visibility of the important features (gates). This improves the reliability of vision-based estimators for localization and can eventually lead to safe autonomous flight. The proposed algorithm is tested in a photorealistic simulation with a high-speed drone racing task.
28.Visual-Semantic Graph Attention Network for Human-Object Interaction Detection ⬇️
In scene understanding, machines benefit from not only detecting individual scene instances but also from learning their possible interactions. Human-Object Interaction (HOI) Detection tries to infer the predicate on a <subject,predicate,object> triplet. Contextual information has been found critical in inferring interactions. However, most works use features from single object instances that have a direct relation with the subject. Few works have studied the disambiguating contribution of subsidiary relations in addition to how attention might leverage them for inference. We contribute a dual-graph attention network that aggregates contextual visual, spatial, and semantic information dynamically for primary subject-object relations as well as subsidiary relations. Graph attention networks dynamically leverage node neighborhood information. Our network uses attention to first leverage visual-spatial and semantic cues from primary and subsidiary relations independently and then combines them before a final readout step. Our network learns to use primary and subsidiary relations to improve inference: encouraging the right interpretations and discouraging incorrect ones. We call our model: Visual-Semantic Graph Attention Networks (VS-GATs). We surpass state-of-the-art HOI detection mAPs in the challenging HICO-DET dataset, including in long-tail cases that are harder to interpret. Code, video, and supplementary information is available at this http URL.