- 1) Papers (Semi-Supervised_Learning)
- ▶ for Considering Domain Adaptation
- ▶ for Data Augmentation
- ▶ for Image Classification
- ▶ for Object Detection
- ▶ for Semantic Segmentation
- ▶ for Pose Estimation
- ▶ for 3D Object Detection
- ▶ for 6D Object Pose Estimation
- ▶ for Rotation Regression (3D Object Pose)
- ▶ for 3D Reconstruction
- ▶ for Crowd Counting
- ▶ for 3D Hand-Object
- ▶ for Face Landmarks
- (github) SemiSeg: a list of "Awesome Semi-Supervised Semantic Segmentation" works
- (github) LAMDA-SSL: Semi-Supervised Learning Algorithms [arxiv link][project homepage]
-
(TPAMI2018) Semi-Supervised Domain Adaptation by Covariance Matching [paper link][
Xi’an Jiaotong University
] -
👍SSDA_MME(ICCV2019) Semi-supervised Domain Adaptation via Minimax Entropy [paper link][arxiv link][project link][code|official][
Boston University
andUniversity of California, Berkeley
] -
ECACL(ICCV2021) ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation [paper link][arxiv link][code|official][
NEC Laboratories, America
andNortheastern University
][the code is based onSSDA_MME
]
-
👍AdaIN (ICCV2017) Arbitrary Style Transfer in Real-Time With Adaptive Instance Normalization [paper link][arxiv link][code|official]
-
👍Cutout (arxiv2017.08) Improved Regularization of Convolutional Neural Networks with Cutout [arxiv link][code|official]
-
👍Mixup (ICLR2018) Mixup: Beyond Empirical Risk Minimization [openreview link][arxiv link][code|official]
-
AdaMixUp (AAAI2019) MixUp as Locally Linear Out-of-Manifold Regularization [paper link][arxiv link][code|official]
-
👍CutMix (ICCV2019) CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features [paper link][arxiv link][code|official]
-
Manifold Mixup (ICML2019) Manifold Mixup: Better Representations by Interpolating Hidden States [paper link][arxiv link][code|official]
-
AutoAugment (CVPR2019) AutoAugment: Learning Augmentation Policies from Data [paper link]][arxiv link][code|official][
google
] -
Fast AutoAugment (NIPS2019) Fast AutoAugment [paper link][openreview link][arxiv link][code|official]
-
👍RandAugment (CVPRW2020) Randaugment: Practical Automated Data Augmentation With a Reduced Search Space [paper link][arxiv link][code|official]
-
PuzzleMix(ICML2020) Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup [paper link][arxiv link][code|official]
-
👍Adversarial AutoAugment Adversarial AutoAugment [openreview link][arxiv link][
Huawei
, code is not available.][It may producemeaningless
ordifficult-to-recognize
images, such asblack and noise
images, if it is not constrained properly.] -
AugMix(ICLR2020) AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty [paper link][arxiv link][code|official][for
improving robustness and uncertainty
anddomain generalization
] -
AugMax(NIPS2021) AugMax: Adversarial Composition of Random Augmentations for Robust Training [paper link][openreview link][code|official][
AugMax-DuBIN
, compared toAugMix
] -
👍NDA (ICLR2021) Negative Data Augmentation [openreview link][arxiv link][code|official][It intentionally creates
out-of-distribution
samples;GAN-based
][It proposes a framework to doNegative Data Augmentation
forgenerative
models andself-supervised learning
] -
MixStyle(ICLR2021) Domain Generalization with MixStyle [openreview link][arxiv link][slides link][code}official][originally designed for
domain generalization
, inspired byAdaIN (ICCV2017)
] -
StyleMix(CVPR2021) StyleMix: Separating Content and Style for Enhanced Data Augmentation [paper link][code|official]
-
KeepAugment(CVPR2021) KeepAugment: A Simple Information-Preserving Data Augmentation Approach [paper link][arxiv link]
-
Augmentation-for-LNL(CVPR2021) Augmentation Strategies for Learning With Noisy Labels [paper link][arxiv link][code|official][Its repository is a fork of the official DivideMix implementation.]
-
AutoDO(CVPR2021) AutoDO: Robust AutoAugment for Biased Data With Label Noise via Scalable Probabilistic Implicit Differentiation [paper link][arxiv link][code|official]
-
TrivialAugment(ICCV2021 oral) TrivialAugment: Tuning-Free Yet State-of-the-Art Data Augmentation [paper link][arxiv link][code|official]
-
RegMixup(NIPS2022) Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness [paper link][arxiv link][code|official]
-
👍C-Mixup(NIPS2022) C-Mixup: Improving Generalization in Regression [paper link][arxiv link][code|official][for the
Regression
task] -
DeepAA(ICLR2022) Deep AutoAugment [openreview link][code|official][
Michigan State University + Amazon Web Services
] -
AutoMix(ECCV2022) AutoMix: Unveiling the Power of Mixup for Stronger Classifiers [paper link][arxiv link][code|official][
Westlake University
] -
TokenMix(ECCV2022) TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers [paper link][arxiv link][code|official]
-
TransMix(CVPR2022) TransMix: Attend To Mix for Vision Transformers [paper link][arxiv link][code|official]
-
TeachAugment(CVPR2022 Oral) TeachAugment: Data Augmentation Optimization Using Teacher Knowledge [paper link][arxiv link][code|official][It uses a teacher model to avoid
meaningless augmentations
. Although it makes reasonable improvements, it has a significant drawback: it involves alternative optimization that relies on an extra model, which significantly increases the training complexity] -
👍YOCO(ICML2022) You Only Cut Once: Boosting Data Augmentation with a Single Cut [paper link][arxiv link][code|official]
-
Soft Augmentation (CVPR2023) Soft Augmentation for Image Classification [paper link][arxiv link][code|official]
-
DualAug(arxiv2023.10) DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection [arxiv link][openreview link (rejected)]
-
Adversarial-AutoMixup(ICLR2024 spotlight)(arxiv2023.12) Adversarial-AutoMixup [openreview link][arxiv link][code|official][
Chongqing Technology and Business University
] -
FeatAug-DETR & DataAug-DETR(TPAMI2024) FeatAug-DETR: Enriching One-to-Many Matching for DETRs With Feature Augmentation [paper link][arxiv link][code|official][
CUHK
, the augmentation ofdata
andfeature
inDETRs
(such asDAB-DETR
,Deformable-DETR
, andH-Deformable-DETR
) is very useful for further designingSSL
methods] -
SUMix(ECCV2024)(arxiv2024.07) SUMix: Mixup with Semantic and Uncertain Information [arxiv link][code|official][
Chongqing Technology and Business University
] -
👍instance_augmentation(ECCV2024)(arxiv2024.06) Dataset Enhancement with Instance-Level Augmentations [arxiv link][code|official][
VGG, University of Oxford + PiñataFarms AI
]
-
Π-model (ICLR2017) Temporal Ensembling for Semi-Supervised Learning [openreview link][arxiv link][
It proposes a temporal ensemble strategy for the pseudo-label to reduce the noise in the target
] -
👍👍Mean Teachers (NIPS2017) Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results [paper link][arxiv link][
the teacher is the moving average of the student which can be timely updated in every iteration
,But their performance is limited because the two models tend to converge to the same point and stop further exploration
] -
VAT (TPAMI2018) Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning [paper link][arxiv link][code|official vat_chainer][code|official vat_tf]
-
DCT (Deep Co-Training)(ECCV2018) Deep Co-Training for Semi-Supervised Image Recognition [paper link][arxiv link][
learn two different models by minimizing their prediction discrepancy
,learn from different initializations to avoid the case where the two models converge to the same point
] -
Dual-Student (ICCV2019) Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning [paper link][
learn two different models by minimizing their prediction discrepancy
,add view difference constraints to avoid the case where the two models converge to the same point
] -
👍MixMatch (NIPS2019) MixMatch: A Holistic Approach to Semi-Supervised Learning [paper link][arxiv link][code|official][
Google
, The first author isDavid Berthelot
,Combining Existing Useful SSL Techniques
] -
👍ReMixMatch (ICLR2020) ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring [openreview link][arxiv link][code|official][
Google
, The first author isDavid Berthelot
,Applying Multiple Strong Augmentations for the Same Input Batch
] -
👍👍FixMatch (NIPS2020) FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence [paper link][arxiv link][code|official][
Google
, The first author isDavid Berthelot
,Weak-Strong Augmentation Pairs
,pseudo-labeling based (also called self-training)
] -
FeatMatch(ECCV2020) FeatMatch: Feature-Based Augmentation for Semi-supervised Learning [paper link][arxiv link][project link][code|official]
-
👍UDA (NIPS2020) Unsupervised Data Augmentation for Consistency Training [paper link][arxiv link][code|official]
-
👍FlexMatch (NIPS2021) FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling [paper link][arxiv link][code|official]
-
Dash (ICML2021) Dash: Semi-Supervised Learning with Dynamic Thresholding [paper link][arxiv link][
It proposes dynamic and adaptive pseudo label filtering, better suited for the training process (similar to the FixMatch)
] -
SimPLE (CVPR2021) SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification [paper link][arxiv link][code|official][
It proposes the paired loss minimizing the statistical distance between confident and similar pseudo labels
] -
SemCo (CVPR2021) All Labels Are Not Created Equal: Enhancing Semi-Supervision via Label Grouping and Co-Training [paper link][arxiv link][code|official][
It considers label semantics to prevent the degradation of pseudo label quality for visually similar classes in a co-training manner
] -
EMAN (CVPR2021) Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning [paper link][arxiv link][code|official][
may not that generic
] -
CoMatch (ICCV2021) CoMatch: Semi-Supervised Learning With Contrastive Graph Regularization [paper link][arxiv link][code|official][
Salesforce Research
, based on `FixMatch] -
CRMatch (arxiv2021.12)(IJCV2023) Revisiting Consistency Regularization for Semi-Supervised Learning [paper link][arxiv link]
-
SAW_SSL(ICML2022) Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data [paper link][code|official]
-
ADSH(ICML2022) Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding [paper link][code|official][
Nanjing University
] -
Classification-SemiCLS (CVPR2022) Class-Aware Contrastive Semi-Supervised Learning [paper link][arxiv link][code|official][based on
FixMatch
,THU + Tencent Youtu Lab
] -
SimMatch (CVPR2022) SimMatch: Semi-Supervised Learning With Similarity Matching [paper link][arxiv link][code|official][
The University of Sydney
] -
USB(NIPS2022) USB: A Unified Semi-supervised Learning Benchmark for Classification [paper link][arxiv link][code|official][
microsoft
] -
Bi-Adaptation(ICML2023) Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions [openreview link][pdf link][
Nanjing University
,SSL (Semi-Supervised Learning) + DA (Domain Adaptation)
] -
FreeMatch (ICLR2023) FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning [openreview link][arxiv link][code|official][
microsoft
] -
SoftMatch (ICLR2023) SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning [openreview link][arxiv link][code|official][
microsoft
] -
FullMatch (CVPR2023) Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data [paper link][arxiv link][code|official][based on
FixMatch
,megvii-research
] -
CHMatch (CVPR2023) CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning [paper link][code|official][based on
FixMatch
andFlexMatch
,Harbin Institute of Technology (Shenzhen)
] -
👍Suave-Daino(CVPR2023) Semi-Supervised Learning Made Simple With Self-Supervised Clustering [paper link][arxiv link][code|official][based on
Self-Supervised
methods such asSwAV
orDINO
] -
ProtoCon(CVPR2023) PROTOCON: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning [paper link][arxiv link][code is unavailable][
Monash University, Australia
] -
SAA (ICCV2023) Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning [paper link][arxiv link][code|official][based on
FixMatch
andFlexMatch
] -
ShrinkMatch (ICCV2023) Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning [paper link][arxiv link][code|official][based on
FixMatch
] -
SimMatchV2 (ICCV2023) SimMatchV2: Semi-Supervised Learning with Graph Consistency [paper link][arxiv link][code|official][
The University of Sydney
, based onFixMatch
andSimMatch
]
-
ssl_detection(arxiv2020.12) A Simple Semi-Supervised Learning Framework for Object Detection [arxiv link][code|official][
google-research
] -
👍Unbiased Teacher (ICLR2021) Unbiased Teacher for Semi-Supervised Object Detection [openreview link][arxiv link][project link][code|official]
-
Unbiased Teacher v2 (CVPR2022) Unbiased Teacher v2: Semi-Supervised Object Detection for Anchor-Free and Anchor-Based Detectors [paper link][arxiv link][project link]
-
MUM (CVPR2022) MUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection [paper link][arxiv link][code|official][
data augmentation
, (arxiv2022.03) Pose-MUM: Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation]] -
👍EfficientTeacher(arxiv2023.02) Efficient Teacher: Semi-Supervised Object Detection for YOLOv5 [arxiv link][code|official][
Alibaba Research
, based onYOLOv5-L
] -
ARSL (CVPR2023) Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection [paper link][arxiv link][code|official of PaddleDetection][
PaddleDetection
] -
MixTeacher (CVPR2023) MixTeacher: Mining Promising Labels With Mixed Scale Teacher for Semi-Supervised Object Detection [paper link][arxiv link][code|official]
-
Semi-DETR (CVPR2023) Semi-DETR: Semi-Supervised Object Detection With Detection Transformers [paper link][arxiv link][code|official][
SYSU
] -
Consistent-Teacher (CVPR2023) Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection [paper link][arxiv link][project link][code|official][
SenseTime Research
]
-
PS-MT(CVPR2022) Perturbed and Strict Mean Teachers for Semi-Supervised Semantic Segmentation [paper link][arxiv link][code|official]
-
UniMatch (CVPR2023) Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation [paper link][arxiv link][code|official]
- Please refer [Transfer Learning of Multiple Person Pose Estimation]
It estimates the category and 3D bounding box for each object in the image. The 3D bounding box can be further divided into 3D center location (x, y, z), dimension (h, w, l) and orientation (yaw angle) θ. The roll and pitch angles of objects are set to 0.
-
👍SESS (CVPR2020 oral) SESS: Self-Ensembling Semi-Supervised 3D Object Detection [paper link][arxiv link][code|official][
National University of Singapore
, comparing toSESS
, on datasetsScanNet
andSUNRGB-D
, usingMean-Teacher
] -
👍👍3DIoUMatch (CVPR2021) 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection [paper link][arxiv link][code|official][
Stanford University + Tsinghua University + NVIDIA
, on datasetsScanNet
,SUNRGB-D
andKITTI
, usingMean-Teacher
andFixMatch
] -
MVC-MonoDet (ECCV2022) Semi-supervised Monocular 3D Object Detection by Multi-view Consistency [paper link][code}official][3D detection on the
KITTI
andnuScenes
datasets] -
Proficient-Teachers (ECCV2022) Semi-supervised 3D Object Detection with Proficient Teachers [paper link][arxiv link][code|official (not really released!!!👎)][
Beijing Institute of Technology
, comparing toSESS
and3DIoUMatch
yet no code, on datasetsONCE
andWaymo Open
, revised based onMean-Teacher
] -
UpCycling (ICCV2023) UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes [paper link][arxiv link][
Seoul National University
, comparing to3DIoUMatch
yet no code, on datasetsScanNet
,SUNRGB-D
andKITTI
] -
ViT-WSS3D (ICCV2023) A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection [paper link][
HUST
, comparing to3DIoUMatch
yet no code, on datasetsSUNRGB-D
andKITTI
] -
Side-Aware (ICCV2023) Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection [paper link][
USTC
, comparing toSESS
and3DIoUMatch
yet no code, usingMean-Teacher
] -
NoiseDet (ICCV2023) Learning from Noisy Data for Semi-Supervised 3D Object Detection [paper link][code|official (not really released!!!👎)][
USTC
, comparing toSESS
and3DIoUMatch
yet no code, on datasetsONCE
andWaymo Open
] -
👍👍DQS3D (ICCV2023) DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection [paper link][arxiv link][code|official][
Institute for AI Industry Research (AIR), Tsinghua University
, comparing toSESS
and3DIoUMatch
, on datasetsScanNet
andSUNRGB-D
, usingMean-Teacher
]
-
multipath(CVPR2020) Multi-Path Learning for Object Pose Estimation Across Domains [paper link][code|official][
Domain Adaptation
,6D Object Detection
,3D Object Pose Estimation
] -
Self6D(ECCV2020) Self6D: Self-Supervised Monocular 6D Object Pose Estimation [paper link][arxiv link][code|official (Self6D-Diff-Renderer)][
THU
] -
Self6D++(TPAMI2021) Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation [paper link][arxiv link][code|official][
THU
] -
DSC-PoseNet(CVPR2021) DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency [paper link][arxiv link][code is not available][
Baidu Research
, a self-supervised manner, needing 2D bounding boxes] -
zero-shot-pose(ECCV2022) Zero-Shot Category-Level Object Pose Estimation [paper link][arxiv link][code|official][
Zero-Shot Learning
,University of Oxford
, on the datasetCO3D
,the authors re-annotated 10 sequences from each of 20 categories with ground-truth poses.
,all baselines are reproduced by the authors.
] -
Self-DPDN(ECCV2022) Category-Level 6D Object Pose and Size Estimation Using Self-supervised Deep Prior Deformation Networks [paper link][arxiv link][code|official][
Self-Supervised
,Domain Adaptation
,South China University of Technology
, another workVI-Net (ICCV2023)
with titleVI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations
] -
👍Wild6D + RePoNet (NIPS2022) Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset [paper link][arxiv link][project link][code|official][
University of California San Diego
, a new datasetWild6D
,Xiaolong Wang
,Yang Fu 付旸
, based on the NOCS] -
UDA-COPE(CVPR2022) UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation [paper link][arxiv link][project link][no code][
Domain Adaptation
,Taeyeop Lee
, based on the NOCS] -
SSC-6D(AAAI2022) Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation [paper link][code|official][
Dalian University of Technology
] -
MAST(IJCAI2023) Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose [paper link][arxiv link][
Domain Adaptation
,Self-Training
] -
👍self-pose(ICLR2023)(arxiv 2022.10) Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild [openreview link][arxiv link][project link][code|official][training and testing on
Wild6D
,Kaifeng Zhang
, second author isYang Fu 付旸
] -
TTA-COPE (CVPR2023) TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation [paper link][arxiv link][project link][Code is not available][
Test-Time Adaptation
,Taeyeop Lee
,The proposed pose ensemble and the self-training loss improve category-level object pose performance during test time under both semi-supervised and unsupervised settings.
, based on the NOCS] -
👍PseudoFlow(ICCV2023) Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation [paper link][arxiv link][code|official][
Yang Hai(海洋)
,Yinlin Hu (胡银林)
] -
SA6D(CoRL2023) SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects [openreview link][project link][arxiv link][
Bosch Center for AI
,robotic manipulation
,few-shot pose estimation (FSPE)
, inputs:a small number of cluttered reference images
] -
Cas6D (arxiv2023.06) Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images [arxiv link][
Few-Shot Learning
,ByteDance
, compared toOnePose++
andGen6D
, trained on datasetsLINEMOD
andGenMOP
, inputs:sparse support views
]
We here also collect supervised learning based Rotation Regression (a.k.a. 3D Object Pose, or Camera Viewpoint Estimation) methods
-
ViewpointsAndKeypoints(CVPR2015) Viewpoints and Keypoints [paper link][arxiv link][code|official][
University of California, Berkeley
, the first authorShubham Tulsiani
] -
RenderForCNN(ICCV2015 Oral) Render for cnn: Viewpoint estimation in images using cnns trained with rendered 3d model views [paper link][arxiv link][project link][code|official][
Stanford University
, tested on datasetPASCAL3D+
, proposed the synthesized datasetRenderForCNN
] -
deep_direct_stat(ECCV2018) Deep Directional Statistics: Pose Estimation with Uncertainty Quantification [paper link][arxiv link][code|official][
MPII
,von Mises
, first authorSergey Prokudin
,Probabilistic representations have been introduced for modeling orientation with uncertainty
] -
StarMap(ECCV2018) StarMap for Category-Agnostic Keypoint and Viewpoint Estimation [paper link][arxiv link][code|official][
The University of Texas at Austin
, tested on datasetsObjectNet3D
andPASCAL3D+
] -
multi-modal-regression(BMVC2018) A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images [pdf link][arxiv link][code|official][
JHUVisionLab
][used extra rendered images inRenderForCNN (ICCV2015)
for training models onPASCAL3D+
, then methodsSpherical_Regression(CVPR2019)
,matrixFisher(NIPS2020)
,Implicit-PDF(ICML2021)
,RotationNormFlow(CVPR2023)
,Image2Sphere(ICLR2023)
,RotationLaplace(ICLR2023)
andRestrictedRepresentations(NIPS2023)
followed this setting] -
Kpt+PnP(CVPR2018) 3D Pose Estimation and 3D Model Retrieval for Objects in the Wild [paper link][arxiv link][
Graz University of Technology, Austria
, tested on datasetPASCAL3D+
][no code
] -
PoseFromShape(BMVC2019) Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects [arxiv link][project link][code|official][tested on datasets
ObjectNet3D
,Pascal3D+
andPix3D
][the first authorYang Xiao (肖洋)
] -
spherical_embeddings(ICML2019) Cross-Domain 3D Equivariant Image Embeddings [paper link][arxiv link][code|official][
University of Pennsylvania + Google Research
, on datasetsShapeNet
,ModelNet
andPASCAL3D+
][It points out thatSpherical CNNs are equivariant to 3D rotations
][also seeImplicit-PDF(ICML2021)
,Image2Sphere(ICLR2023)
andRestrictedRepresentations(NIPS2023)
which are partly inspired by this work.] -
👍 (CVPR2019) On the Continuity of Rotation Representations in Neural Networks [paper link][arxiv link][
University of Southern California
, the first authorYi Zhou
,Gram-Schmidt orthogonalization procedure
][ForRotation Regression
, this paper validated that parameterization in four or fewer dimensions will bediscontinuous
(this applies to all classic representations such asEuler angles
,axis-angle
, andunit quaternions
)] -
👍Spherical_Regression(CVPR2019) Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on N-Spheres [paper link][arxiv link][code|official][
University of Amsterdam
, the first authorShuai Liao
, proposed the datasetModelNet10-SO3
] -
deep_bingham(ICLR2020) Deep Orientation Uncertainty Learning based on a Bingham Loss [openreview link][code|official][
MIT
,Bingham distributions
, first authorIgor Gilitschenski
,Probabilistic representations have been introduced for modeling orientation with uncertainty
] -
bingham-rotation-learning(QCQP)(RSS2020)(Best Student Paper Award Winner) A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty [paper link][arxiv link][project link][code|official][
University of Toronto + MIT
, first authorValentin Peretroukhin
][The unit quaternion that best aligns two point sets can be computed via the eigendecomposition of a symmetric data matrix, and the proposed network model regresses directly the elements of this 4x4 symmetric matrix.
] -
DeepBinghamNetworks(arxiv2020.12)(IJCV2022) Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation [paper link][arxiv link][project link][code|official][
Stanford University + Technical University of Munich
][The extended version of paperMultimodal Inference for 6D Camera Relocalization and Object Pose Estimation (ECCV2020)
] -
👍 (NIPS2020) An Analysis of SVD for Deep Rotation Estimation [paper link][arxiv link][
Simon Fraser University
, the first authorJake Levinson
,FisherMatch
is partially based on thematrix Fisher distribution
theory introduced in this paper.][pointed out two previous methods modeling the uncertainty of 3D rotation estimation:deep_direct_stat(ECCV2018)
anddeep_bingham(ICLR2020)
.] -
👍 (NIPS2020) Probabilistic Orientation Estimation with Matrix Fisher Distributions [paper link][arxiv link][code|official][
KTH
, the first authorDavid Mohlin
,FisherMatch
is based on thematrix Fisher distribution
theory introduced in this paper.][matrix Fisher distribution
--> (1977) The von Mises–Fisher Matrix Distribution in Orientation Statistics][The visualiztion is adopted from --> (TAC2018) Bayesian Attitude Estimation with the Matrix Fisher Distribution on SO(3) (arxiv link)][pointed out two previous methods modeling the uncertainty of 3D rotation estimation:deep_direct_stat(ECCV2018)
anddeep_bingham(ICLR2020)
.][applying thematrix Fisher parameters
forHuman Mesh Recovery
in work(CVPR2023) Learning Analytical Posterior Probability for Human Mesh Recovery
] -
PoseContrast(3DV2021 Oral) PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning [paper link][arxiv link][project link][code|official][tested on datasets
ObjectNet3D
,Pascal3D+
andPix3D
][the first authorYang Xiao (肖洋)
] -
NeMo(ICLR2021) NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [openreview link][arxiv link][code|official][
Johns Hopkins University
, tested on datasetsObjectNet3D
,OccludedPASCAL3D+
andPASCAL3D+
][the first authorAngtian Wang
] -
👍Implicit-PDF(ICML2021) Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold [paper link][arxiv link][project link][code|official][
Google Research
, the first authorKieran A Murphy
,awesome visualization of SO(3)
][The technical design choices of implicit pose model in this paper are inspired by the very successful implicit shape (OccupancyNetworks
) and scene (NeRF
) representations, which can represent detailed geometry with a multilayer perceptron that takes low-dimensional position and/or directions as inputs.][IPDF is quite good at outputtingmultiple 3D pose candidates
for symmetry objects.] -
RPMG(CVPR2022) Projective Manifold Gradient Layer for Deep Rotation Regression [paper link][arxiv link][project link][code|official][
PKU
, the first authorJiayi Chen | 陈嘉毅
] -
AcciTurn(ICCVW2023) Accidental Turntables: Learning 3D Pose by Watching Objects Turn [paper link][arxiv link][project link][dataset link][
University of Massachusetts - Amherst + Adobe Research
] -
RotationNormFlow(CVPR2023) Delving into Discrete Normalizing Flows on SO (3) Manifold for Probabilistic Rotation Modeling [paper link][arxiv link][project link][code|official][
PKU
, the first authorYulin Liu 刘雨霖
, it is also proposed by the co-author ofFisherMatch
] -
Image2Sphere(ICLR2023)(notable-top-5%) Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction [openreview link][arxiv link][project link][code|official][
Northeastern University
, the first authorDavid M. Klee
] -
RotationLaplace(ICLR2023)(notable-top-25%) A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation [openreview link][arxiv link][project link][code|official][
PKU
, the first authorYingda Yin 尹英达
] -
VoGE(ICLR2023)(Poster) VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis [openreview link][arxiv link][code|official][following the
Analysis-by-Synthesi
pattern asNeMo
][Johns Hopkins University
, tested on datasetsObjectNet3D
,OccludedPASCAL3D+
andPASCAL3D+
][the first authorAngtian Wang
] -
RestrictedRepresentations(NIPS2023)(arxiv2023.06) Equivariant Single View Pose Prediction Via Induced and Restricted Representations [openreview link][arxiv link][
Northeastern University
, the first authorOwen Howell
, on datasetsPASCAL3D+
andSYMSOL
,Machine Learning, Group Theory
] -
RnC(NIPS2023, Spotlight)(arxiv2022.10) Rank-N-Contrast: Learning Continuous Representations for Regression [paper link][openreview link][arxiv link][code|official][
MIT CSAIL + GIST
] -
(arxiv2024.04) Learning a Category-level Object Pose Estimator without Pose Annotations [arxiv link][
Xi’an Jiaotong Univeristy + Johns Hopkins University + Tsinghua University + University of Freiburg + MPII
][based onZero-1-to-3
; tested on datasetsPASCAL3D+
andKITTI
]
-
FSDetView(ECCV2020) Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild [paper link][arxiv link][project link][tested on datasets
ObjectNet3D
andPascal3D+
] -
FSDetView(TPAMI2022) Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild [paper link][arxiv link][project link][tested on datasets
ObjectNet3D
,Pascal3D+
andPix3D
][the first to conduct thisjoint task of object detection and viewpoint estimation
in thefew-shot
regime.]
-
SSV(CVPR2020) Self-Supervised Viewpoint Learning From Image Collections [paper link][arxiv link][code|official][
Unsupervised Learning
,Head Pose Estimation
, trained on300W-LP
and tested onBIWI
,NVlabs
] -
ViewNet(ICCV2021) ViewNet: Unsupervised Viewpoint Estimation From Conditional Generation [paper link][arxiv link][
Unsupervised Learning
, trained onPASCAL3D+
,University of Edinburgh
] -
NVSM(NIPS2021) Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose [paper link][arxiv link][code|official][
Johns Hopkins University
, trained onPASCAL3D+
andKITTI
] -
👍FisherMatch(CVPR2022 Oral) FisherMatch: Semi-Supervised Rotation Regression via Entropy-Based Filtering [paper link][arxiv link][project link][code|official][
PKU
, the first authorYingda Yin 尹英达
][The visualizaion of matrix Fisher distribution so3_distribution_visualization][3DoF rotation estimation
, based onFixMatch
andSemi_Human_Pose
, maybe suitable for3D head pose estimation
, theSemi-Supervised Rotation Regression
task] -
UCVME(AAAI2023) Semi-Supervised Deep Regression with Uncertainty Consistency and Variational Model Ensembling via Bayesian Neural Networks [paper link][arxiv link][code | official][
Semi-Supervised Rotation Regression
] -
FisherMatch+(arxiv2023.05)(submitted to TPAMI) Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution [arxiv link][It proposed a new robust
probabilistic modeling
method; It is an extended version ofFisherMatch
]
-
3d-recon(ECCV2018) Learning Single-View 3D Reconstruction with Limited Pose Supervision [paper link][pdf link][code|official][
Guandao Yang (杨关道)
], may still needing additional annotations such ascamera pose
] -
(CVPRW2020) Semi-Supervised 3D Face Representation Learning From Unconstrained Photo Collections [paper link][
Multiple Images as Inputs
] -
SSR(ICCVW2021) SSR: Semi-Supervised Soft Rasterizer for Single-View 2D to 3D Reconstruction [paper link][arxiv link][code|official][may still needing additional annotations such as
silhouette
] -
SSP3D(ECCV2022) Semi-supervised Single-View 3D Reconstruction via Prototype Shape Priors [paper link][arxiv link][code|official][
Zhen Xing
, on datasetsShapeNet
andPix3D
][based onmean-teacher
and proposed two modules namelyPrototype Attention Module
(using multi-head self-attention) andShape Naturalness Module
(a generative adversarial learning manner)] -
OF4HMR(TMLR2024) Using Motion Cues to Supervise Single-frame Body Pose & Shape Estimation in Low Data Regimes [openreview link][arxiv link][code|official][
CVLab, EPFL
+Meta AI
] -
Real3D(arxiv2024.06) Real3D: Scaling Up Large Reconstruction Models with Real-World Images [arxiv link][project link][code|official][
UT Austin
][The input contains onlyone single object instance
][We scale up training data ofsingle-view LRMs
by enablingself-training
onin-the-wild
images][The real data forself-training
involvesMVImgNet
and ourcollected real data
. The data fortesting
involvesMVImgNet
,CO3D
,OmniObject3D
and our real data.][It is based on the TripoSR, which is theTripoSR: Fast 3D Object Reconstruction from a Single Image
]
-
IRAST(ECCV2020) Semi-supervised Crowd Counting via Self-training on Surrogate Tasks [paper link][arxiv link][
Sichuan University
] -
UA_crowd_counting(ICCV2021) Spatial Uncertainty-Aware Semi-Supervised Crowd Counting [paper link][arxiv link][code|official]
-
MTCP(TNNLS2023) Multi-Task Credible Pseudo-Label Learning for Semi-Supervised Crowd Counting [paper link][code|official][
TJU
] -
OPT(CVPR2023) Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting [paper link][code|official]
-
CrowdCLIP(CVPR2023) CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model [paper link][arxiv link][code|official][
HUST
] -
SSCC (ICCV2023) Calibrating Uncertainty for Semi-Supervised Crowd Counting [paper link][arxiv link][
Stony Brook University
,Mean-Teacher framework
,A new uncertainty estimation branch
]
-
Semi-Hand-Object(CVPR2021) Semi-Supervised 3D Hand-Object Poses Estimation With Interactions in Time [paper link][arxiv link][project link][code|official][trained on
HO3D
dataset,UC San Diego
andNVIDIA
,hand pose estimation
+6-DoF object pose estimation
][using theMANO
hand 3DMM model] -
S2Contact(ECCV2022) S2Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning [paper link]][arxiv link][project link][code|official][
University of Birmingham, UNIST, SUSTech
] -
THOR-Net(WACV2023) THOR-Net: End-to-End Graformer-Based Realistic Two Hands and Object Reconstruction With Self-Supervision [paper link][arxiv link][code|official][
DFKI-AV Kaiserslautern + TU Kaiserslautern + NUST-SEECS Pakistan + UPM Saudi Arabia
] -
SHAR(CVPR2023) Semi-supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discrimination [paper link][arxiv link][project link][
Ynagang Wang
]
-
(CVPR2018) Improving Landmark Localization With Semi-Supervised Learning [paper link][arxiv link][
MILA-University of Montrea
andNVIDIA
] -
TS3(Teacher Supervises StudentS)(ICCV2019) Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection [paper link][
Southern China University of Science and Technology
andBaidu
] -
LaplaceKL(ICCV2019) Laplace Landmark Localization [paper link][arxiv link][
Northeastern University
, It proposes a new lossLaplaceKL
; this method can be trained under the SSL setting] -
PIPNet(IJCV2021) Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild [paper link][arxiv link][code|official][
HKUST
, the first authorHaibo Jin
] -
(CVPR2022) Which Images To Label for Few-Shot Medical Landmark Detection? [paper link][arxiv link][
CAS
,Medical Image
] -
FaceLift(CVPR2024)(arxiv2024.05) FaceLift: Semi-supervised 3D Facial Landmark Localization [paper link][arxiv link][project link][
Flawless AI
]