Skip to main content
buildradar
Sign in
Topic · vision-transformer

vision-transformer

Tracked open-source repos tagged vision-transformer, sorted by stars.

45 repos
  • semantic-segmentation@sithu31296

    SOTA Semantic Segmentation Models in PyTorch

    942-1Star change over the last 7 days
  • FasterViT@NVlabs

    [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

    925+0Star change over the last 7 days
  • AlphaCLIP@SunzeY

    [CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

    875+1Star change over the last 7 days
  • parseq@baudm

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

    738+0Star change over the last 7 days
  • unicom@deepglint

    Large-Scale Visual Representation Model

    702+0Star change over the last 7 days
  • swin2sr@mv-lab

    [ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr

    694+3Star change over the last 7 days
  • openmixup@Westlake-AI

    CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark

    658+0Star change over the last 7 days
  • TransMorph: Transformer for Unsupervised Medical Image Registration (PyTorch)

    632+0Star change over the last 7 days
  • RAG-Driven-Generative-AI@Denis2054

    This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models for generation and evaluation.

    624+2Star change over the last 7 days
  • HIPT@mahmoodlab

    Hierarchical Image Pyramid Transformer - CVPR 2022 (Oral)

    620+0Star change over the last 7 days
  • eomt@tue-mps

    [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

    620+0Star change over the last 7 days
  • LAMDA-PILOT@LAMDA-CL

    🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox

    601+4Star change over the last 7 days
  • DehazeFormer@IDKiro

    Vision Transformers for Single Image Dehazing

    587+3Star change over the last 7 days
  • actionformer_release@happyharrycn

    Code release for ActionFormer (ECCV 2022)

    575+2Star change over the last 7 days
  • Transformers 3rd Edition

    504+2Star change over the last 7 days
← Back to topics