Stars
PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.
An open source implementation of CLIP.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video ta…
CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View
Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.
[CVPR 2022] DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
Language-Driven Semantic Segmentation
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)
CVPR 2021 VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild
Official repository for "Intriguing Properties of Vision Transformers" (NeurIPS 2021--Spotlight)
Semi-supervised Semantic Segmentation with Directional Context-aware Consistency (CVPR 2021)
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
[CVPR 2021] Official PyTorch implementation for Transformer Interpret 6DFA ability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
ICCV2021 (Oral) - Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Code for our ACMMM2020 paper "Context-aware Feature Generation for Zero-shot Semantic Segmentation".
A non-JIT version implementation / replication of CLIP of OpenAI in pytorch
[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers