Lists (24)
3D Vision
object reconstruction, size estimation, etc.Adversarial Attacks & Robustness
probe the robustness of deep modelsCommercial Projects
Datasets
Deep Feature Understanding
Foundation Models
Big modelsFSL
few-shot learning & tasksFSS
Generative Model
GAN/VAE/Flow/DiffusionGraphNet
Image Classification Models
Image classification modelsImage Generation & Editing
Keypoint/Pose Estimation
Some popular bottom-up and top-down pose estimation modelsLabelTool
Matching & Keypoints
Measure_MACs_FLOPs
Object Detection
OCR
Presentation
PPT, Poster, TalkSegmentation
Self/Unsupervised Learning
Shape analysis
ViT & Self-atttention
From transformer (language model) to vision transformer (ViT)webpages
Some nice webpage templatesStars
Official implementation of "EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation" (ICML 2025)
Segment Anything in Medical Images
OpenMMLab Text Detection, Recognition and Understanding Toolbox
Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
⚡ TabPFN: Foundation Model for Tabular Data ⚡
This repositary introduces a suite of novel methods for few-shot keypoint detection (FSKD), including the visual prior guided vision transformer (VPViT), transductive FSKD, and masking and alignmen…
Official PyTorch implementation of "Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data"
MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
zauberzeug / darknet_alexeyAB
Forked from AlexeyAB/darknetWindows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Refine high-quality datasets and visual AI models
Opening Prompt Diversity for Zero-and Few-shot Keypoint Detection
[ECCV 2024] Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation - MMDMC Dataset
A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]
The official repo for ECCV'22 paper: Pose for Everything: Towards Category-Agnostic Pose Estimation
Official Implementation for "Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation", CVPR 2023.
official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”
Graph Neural Network Library for PyTorch
[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"
A latent text-to-image diffusion model
High-Resolution Image Synthesis with Latent Diffusion Models