Alternatives and similar repositories for Battle-of-the-Backbones:

Users that are interested in Battle-of-the-Backbones are comparing it to the libraries listed below

• kirill-vish / Beyond-INet
  Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"
  ☆100Updated 5 months ago
• hamidkazemi22 / vit-visualization
  ☆182Updated last year
• UCSC-VLAA / CLIPA
  [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"
  ☆309Updated 8 months ago
• google-research / syn-rep-learn
  Learning from synthetic data - code and models
  ☆310Updated last year
• all-things-vits / code-samples
  Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.
  ☆181Updated last year
• kaiyuyue / nxtp
  Object Recognition as Next Token Prediction (CVPR 2024 Highlight)
  ☆172Updated last month
• gstoica27 / ZipIt
  A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…
  ☆293Updated last year
• facebookresearch / ssl-data-curation
  PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning
  ☆144Updated 8 months ago
• awaisrauf / Awesome-CV-Foundational-Models
  ☆497Updated 3 months ago
• bfshi / scaling_on_scales
  When do we not need larger vision models?
  ☆368Updated last week
• wysoczanska / clip_dinoiser
  Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.
  ☆233Updated 3 months ago
• LeapLabTHU / EfficientTrain
  1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundatio…
  ☆217Updated 5 months ago
• facebookresearch / dropout
  Code release for "Dropout Reduces Underfitting"
  ☆312Updated last year
• WalBouss / LeGrad
  ☆62Updated 4 months ago
• moein-shariatnia / Pix2Seq
  Simple Implementation of Pix2Seq model for object detection in PyTorch
  ☆122Updated last year
• WalBouss / GEM
  [CVPR24] Official Implementation of GEM (Grounding Everything Module)
  ☆109Updated 3 months ago
• facebookresearch / clip-rocket
  Code release for "Improved baselines for vision-language pre-training"
  ☆60Updated 9 months ago
• berkeley-hipie / HIPIE
  [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"
  ☆281Updated 10 months ago
• LAION-AI / scaling-laws-openclip
  Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
  ☆159Updated last year
• YuchenLiu98 / COMM
  Pytorch code for paper From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
  ☆192Updated last month
• UX-Decoder / FIND
  [NeurIPS 2024] Official implementation of the paper "Interfacing Foundation Models' Embeddings"
  ☆120Updated 6 months ago
• apple / ml-veclip
  The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"
  ☆239Updated 3 weeks ago
• Haiyang-W / GiT
  [ECCV2024 Oral🔥] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
  ☆329Updated last month
• lukemelas / deep-spectral-segmentation
  [CVPR 2022] Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
  ☆233Updated 2 years ago
• mlfoundations / model-soups
  Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
  ☆446Updated 7 months ago
• facebookresearch / r-mae
  PyTorch implementation of R-MAE https//arxiv.org/abs/2306.05411
  ☆110Updated last year
• LightDXY / FT-CLIP
  CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
  ☆211Updated 2 years ago
• naver-ai / cl-vs-mim
  (ICLR 2023) Official PyTorch implementation of "What Do Self-Supervised Vision Transformers Learn?"
  ☆105Updated 11 months ago
• kyegomez / Vit-RGTS
  Open source implementation of "Vision Transformers Need Registers"
  ☆163Updated 3 weeks ago
• facebookresearch / hiera
  Hiera: A fast, powerful, and simple hierarchical vision transformer.
  ☆950Updated 11 months ago