[CVPR 2025] DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation & [ICLR 2024] DFormer & [NeuriPS 2025] OmniSegmentor

Official repository of paper titled "CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications"

Zhu Han, Jin Yang, Lianru Gao, Zhiqiang Zeng, Bing Zhang, Jocelyn Chanussot. Dual-Branch Subpixel-Guided Network for Hyperspectral Image Classification, IEEE TGRS, 2024

Multi-scale Attention Network for Single Image Super-Resolution (CVPRW 2024)

Official code of "HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection".

FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection

This is an official code for UniConvNet on ICCV 2025

[BMVC 2024] Official repository of the paper titled "MSA^2 Net: Multi-scale Adaptive Attention-guided Network for Medical Image Segmentation"

Official ImageNet Model repository

InceptionNeXt: When Inception Meets ConvNeXt (CVPR 2024)

[ICCV2025 highlight]Rectifying Magnitude Neglect in Linear Attention

[ICLR 2025 Spotlight] Official Implementation for ToST (Token Statistics Transformer)

[CVPR 2023] Efficient Frequency Domain-based Transformer for High-Quality Image Deblurring

CVPR2025 - CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution

[NeurIPS25 Spotlight] Official Implementation for CBSA (Contract-and-Broadcast Self-Attention)

Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" - MICCAI 2021

[ICCV'23] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications

Official repository of Polarity-aware Linear Attention for Vision Transformers (ICLR 2025)

The official code of "Rethinking Local Perception in Lightweight Vision Transformer"

[Neural Networks 2025] Dual Selective Fusion Transformer Network for Hyperspectral Image Classification

[IEEE TGRS 2025] ASCNet: Asymmetric Sampling Correction Network for Infrared Image Destriping