The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Official implementation of CVPR2024 Paper "Poly Kernel Inception Network for Remote Sensing Detection".

Official repo for "[ICCV 2025] Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling"

[ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers than Transformers for ConvNets?"

The official implementation of the paper "Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation"

Official repository of Agent Attention (ECCV2024)

Code of ICLR2023 paper "TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding" and ECCV2022 paper "Inverted Pyramid Multi-task Transformer for Dense Scene Understanding"

This is a PyTorch re-implementation of Axial-DeepLab (ECCV 2020 Spotlight)

Implementation of Axial attention - attending to multi-dimensional data efficiently

A lightweight utility for detecting the horizon line in natural images.

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

a novel real-time model in semantic segmentation

xLSTM as Generic Vision Backbone

[CVPR 2024] Official implement of <Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation>

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025)

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

code and trained models for "Attentional Feature Fusion"

[CVPR 2024] Code release for TransNeXt model

Official repository of ACmix (CVPR2022)

[ECCV2024] Official implementation of paper, "DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs".

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

PyTorch Examples repo for "ReZero is All You Need: Fast Convergence at Large Depth"

Temporally Consistent Horizon Lines

用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序

An Autonomous LLM Agent for Complex Task Solving

FcaNet: Frequency Channel Attention Networks

📷 EasyPhoto | Your Smart AI Photo Generator.