deep learning for image processing including classification and object-detection etc.

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

OpenMMLab FewShot Learning Toolbox and Benchmark

OBBDetection is an oriented object detection library, which is based on MMdetection.

try to implement the CVPR 2019 paper "Selective Kernel Networks" by PyTorch

PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

Official PyTorch Implementation of Learning What Not to Segment: A New Perspective on Few-Shot Segmentation (CVPR'22 Oral & TPAMI'23).

CrossKD: Cross-Head Knowledge Distillation for Dense Object Detection

[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

The official implementation of BackTAL, TPAMI 2021.

The official code for our ECCV22 oral paper: tracking objects as pixel-wise distributions.

FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment

Official code for "Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer. ICCV2021".

[CVPR'22] Official PyTorch implementation of Integrative Few-Shot Learning for Classification and Segmentation

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation (CVPR 2021)

[CVPR'22] Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models

code for CVPR paper Zero-shot Instance Segmentation

The code for OpenmmLab challenge.

ACFNet: Attentional Class Feature Network for Semantic Segmentation.(ICCV2019)

[NeurIPS 2022] Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning

This is the official implementation of the ECCV'2022 paper "Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation".

Official Pytorch implementation of Multi-Similarity and Attention Guidence for Boosting Few-Shot Segmentation.

Official pytorch implementation of CPSL: class-balanced pixel-level self-labeling for domain adaptive semantic segmentation (CVPR 2022)

Anchor-free Oriented Proposal Generator for Object Detection