(CVPR 2021 Oral) Open World Object Detection
-
Updated
Dec 19, 2022 - Python
(CVPR 2021 Oral) Open World Object Detection
The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R&D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation net…
Code for reproducing results in the sliced score matching paper (UAI 2019)
Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
[NeurIPS 2022] (Amortized) distributional control for pre-trained generative models
[NeurIPS 2021 Spotlight] Learning to Compose Visual Relations
A PyTorch implementation of Implicit Behavioral Cloning
[AAAI 2022] Official Implementation of Active Learning for Domain Adaptation: An Energy-based Approach https://arxiv.org/abs/2112.01406
Extreme Q-Learning: Max Entropy RL without Entropy
[ICCV 2023] Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models
Code for Weakly Supervised Energy-Based Learning for Action Segmentation (ICCV 2019 Oral)
Official implementation of "Accurate 3D Object Detection using Energy-Based Models", CVPR Workshops 2021.
(CVPR 2022) Energy-based Latent Aligner for Incremental Learning
Some toy examples of score matching algorithms written in PyTorch
The official repository of "Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models".
[NeurIPS 2021] Unsupervised Foreground Extraction via Deep Region Competition
[CVPR 2024] TEA: Test-time Energy Adaptation
Noise Contrastive Estimation (NCE) in PyTorch
This repository contains the official code for Energy Transformer---an efficient Energy-based Transformer variant for graph classification
PyTorch implementation of JEM++: Improved Techniques for Training JEM
Add a description, image, and links to the energy-based-model topic page so that developers can more easily learn about it.
To associate your repository with the energy-based-model topic, visit your repo's landing page and select "manage topics."