D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement 💥💥💥

Segment Matting is a project aimed at improving the quality and performance of image matting using the SAM (Segment Anything Model) model. It focuses on optimizing the matting process to reduce jag…

[ICCV 2021 Oral] Deep Evidential Action Recognition

Serve, optimize and scale PyTorch models in production

[NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim

This repo contains a PyTorch implementation of the paper: "Evidential Deep Learning to Quantify Classification Uncertainty"

Refine high-quality datasets and visual AI models

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

🔥🔥🔥TensorRT for YOLOv8、YOLOv8-Pose、YOLOv8-Seg、YOLOv8-Cls、YOLOv7、YOLOv6、YOLOv5、YOLONAS......🚀🚀🚀CUDA IS ALL YOU NEED.🍎🍎🍎

[ICCV'21] Official PyTorch implementation of Relational Embedding for Few-Shot Classification

[ACM MM2024] Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation

High-resolution models for human tasks.

A curated list of foundation models for vision and language tasks

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Low rank adaptation for segmentation anything model (SAM)

[CVPR 2024] Code for our Paper "DeiT-LT: Distillation Strikes Back for Vision Transformer training on Long-Tailed Datasets"

[ECCV2024] ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

[ECCV 2024] Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

The Paper List of Large Multi-Modality Model, Parameter-Efficient Finetuning, Vision-Language Pretraining, Conventional Image-Text Matching for Preliminary Insight.

[T-PAMI-2024] Transformer-Based Visual Segmentation: A Survey

PyTorch code and pretrained weights for the UNIC models.

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

A list of video object segmentation (VOS) papers

[ECCV2024] Official implementation of Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

Images to inference with no labeling (use foundation models to train supervised models).

The most impactful papers related to contrastive pretraining for multimodal models!

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2