Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)

Code for the paper: "Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress"

Collect super-resolution related papers, data, repositories

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Real-time portrait segmentation for mobile devices

ECCV'2024 "GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition"

(CVPR 2024) Bridging the Gap Between End-to-End and Two-Step Text Spotting.

OCR, layout analysis, reading order, line detection in 90+ languages

Export Segment Anything Models to ONNX

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

Turning a CLIP Model into a Scene Text Detector (CVPR2023) | Turning a CLIP Model into a Scene Text Spotter (TPAMI)

The HierText dataset contains ~12k images from the Open Images dataset v6 with large amount of text entities. We provide word, line and paragraph level annotations.

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)

OpenMMLab Text Detection, Recognition and Understanding Toolbox

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

[arXiv preprint] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

CAMixerSR: Only Details Need More “Attention” (CVPR 2024)

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[ECCV 2024] Official implementation of the paper "Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning"

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

[ECCV2024 Oral] Official implementation of the paper "Relation DETR: Exploring Explicit Position Relation Prior for Object Detection"

Understanding Deep Learning - Simon J.D. Prince

Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

Code release for "Segment Anything without Supervision"

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

EfficientViT is a new family of vision models for efficient high-resolution vision.

[CVPR 2024] PTQ4SAM: Post-Training Quantization for Segment Anything