vealocia's Stars
facebookincubator/submitit
Python 3.8+ toolbox for submitting jobs to Slurm
gaopengcuhk/Pretrained-Pix2Seq
Replication of Pix2Seq with Pretrained Model
salesforce/ALPRO
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
synercys/annotated_latex_equations
Examples of how to create colorful, annotated equations in Latex using Tikz.
youngwanLEE/MPViT
[CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction
google-research/vmoe
mlfoundations/wise-ft
Robust fine-tuning of zero-shot models
isl-org/lang-seg
Language-Driven Semantic Segmentation
facebookresearch/ConvNeXt
Code release for ConvNeXt model
mlfoundations/open_clip
An open source implementation of CLIP.
facebookresearch/Detic
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
JunMa11/SegLossOdyssey
A collection of loss functions for medical image segmentation
julvo/reloading
Change Python code while it's running without losing state
facebookresearch/mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
yan-hao-tian/VW
iclr2024 poster Varying Window Attention
ucasligang/SimViT
[ICME 2022] code for the paper, SimVit: Exploring a simple vision transformer with sliding windows.
FingerRec/OA-Transformer
[CVPR 2022] The code for our paper 《Object-aware Video-language Pre-training for Retrieval》
BUPT-PRIV/MAE-priv
ytongbai/ViTs-vs-CNNs
[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)
zhirongw/lemniscate.pytorch
Unsupervised Feature Learning via Non-parametric Instance Discrimination
open-mmlab/mmselfsup
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
WXinlong/DenseCL
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.
lichengunc/refer
Referring Expression Datasets API
open-mmlab/mmdeploy
OpenMMLab Model Deployment Framework
MCG-NJU/MMN
[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
microsoft/CodeBERT
CodeBERT
sajjjadayobi/CLIPfa
CLIPfa: Connecting Farsi Text and Images
lucidrains/x-clip
A concise but complete implementation of CLIP with various experimental improvements from recent papers
RangiLyu/nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
HobbitLong/RepDistiller
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods