Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;

Cascade Graph Neural Networks for RGB-D Salient Object Detection (ECCV20)

[CVPR 2024] Official implementation for "Equivariant Multi-Modality Image Fusion."

The code of " Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network"

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Models and examples built with TensorFlow

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

DIVFusion: Darkness-free infrared and visible image fusion

A tool to magnify the local areas of images.

Official pytorch code of our paper "MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection"

All deep learning-based infrared and visible image fusion algorithms in a whole framework

A simple and efficient Mamba implementation in pure PyTorch and MLX.

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

[IEEE TIP 2024] DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention

RFN-Nest(Information Fusion, 2021, Highly Cited Paper) - PyTorch =1.5，Python=3.7

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

MSRS: Multi-Spectral Road Scenarios for Practical Infrared and Visible Image Fusion

LRRNet (IEEE TPAMI 2023, Highly Cited Paper), Python 3.7, Pytorch >=1.8

PyTorch code for our ICCV 2023 paper "Dual Aggregation Transformer for Image Super-Resolution"

Official Open Source code for "Scaling Language-Image Pre-training via Masking"

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval (CVPR 2023)

Word4Per is an innovative framework for Zero-Shot Composed Person Retrieval (ZS-CPR), integrating visual and textual information for enhanced person identification. This repository includes the Wor…

An open source implementation of CLIP.

[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features

[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.