Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[ICCV 2023] You Only Look at One Partial Sequence
| Date | Stars |
|---|---|
| 2026-07-24 | 343 |
| 2026-07-25 | 343 |
| 2026-07-28 | 343 |
| 2026-07-30 | 343 |
| 2026-09-20 | 343 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <h1>MIMDet 🎭</h1> <h3>Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection</h3> [Yuxin Fang](https://bit.ly/YuxinFang_GoogleScholar)<sup>1</sup> \*, [Shusheng Yang](https://scholar.google.com/citations?user=v6dmW5cntoMC&hl=en)<sup>1</sup> \*, [Shijie Wang](https://github.com/simonJJJ)<sup>1</sup> \*, [Yixiao Ge](https://geyixiao.com/)<sup>2</sup>, [Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ&hl=en)<sup>2</sup>, [Xinggang Wang](https://xinggangw.info/)<sup>1 :email:</sup>, <sup>1</sup> [School of EIC, HUST](http://eic.hust.edu.cn/English/Home.htm), <sup>2</sup> [ARC Lab, Tencent PCG](https://arc.tencent.com/en/index). (\*) equal contribution, (<sup>:email:</sup>) corresponding author. **ICCV 2023** [[paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_Unleashing_Vanilla_Vision_Transformer_with_Masked_Image_Modeling_for_Object_ICCV_2023_paper.pdf)] </div> # ### News * **`19 May, 2022`:** We update our [preprint](https://arxiv.org/abs/2204.02964v2) with stronger results and more analysis. Code & models are also updated in the [`main`](https://github.com/hustvl/MIMDet/tree/main) branch. For our previous results (code & models), please refer to the [`v1.0.0`](https://github.com/hustvl/MIMDet/tree/v1.0.0) branch. * **`6 Apr, 2022`:** Code & models are released! ## Introduction <p align="center"> <img src="MIMDet.png" width=80%> </p> This repo provides code and pretrained models for **MIMDet** (**M**asked **I**mage **M**odeling for **Det**ection). * MIMDet is a simple framekwork that enables a MIM pretrained vanilla ViT to perform high-performance object-level understanding, e.g, object detection and instance segmentation. * In MIMDet, a MIM pre-trained vanilla ViT encoder can work surprisingly well in the challenging object-level recognition scenario even with randomly sampled *partial* observations, e.g., only 25%~50% of the input embeddings. * In order to construct multi-scale representations for object detection, a *randomly initialized* compact convolutional stem supplants the pre-trained large kernel patchify stem, and its intermediate features can naturally serve as the higher resolution inputs of a feature pyramid without upsampling. While the pre-trained ViT is only regarded as the third-stage of our detector's backbone instead of the whole feature extractor, resulting in a ConvNet-ViT *hybrid* architecture. * MIMDet w/ ViT-Base & Mask R-CNN FPN obtains **51.7 box AP** and **46.2 mask AP** on COCO. With ViT-L, MIMDet achieves **54.3 box AP** and **48.2 mask AP**. * We also provide an unofficial implementation of [Benchmarking Detection Transfer Learning with Vision Transformers](https://arxiv.org/abs/2111.11429) that successfully reproduces its reported results. ## Models and Main Results ### Mask R-CNN | <sub>Model | <sub>Sample Ratio | <sub>Schedule | <sub>Aug | <sub>Box AP | <sub>Mask AP | <sub>#params | <sub>config | <sub>model / log | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | <sub>**MIMDet-ViT-B** | <sub>0.5 | <sub>3x | <sub>[480-800, 1333] w/crop | <sub>51.7 | <sub>46.2 | <sub>127.96M | <sub>[config](configs/mimdet/mimdet_vit_base_mask_rcnn_fpn_sr_0p5_800_1333_4xdec_coco_3x.py) | <sub>[model](https://github.com/hustvl/Storage/releases/download/v1.2.0/mimdet_vit_base_mask_rcnn_fpn_sr_0p5_800_1333_4xdec_coco_3x.pth) / [log](https://github.com/hustvl/Storage/releases/download/v1.2.0/mimdet_vit_base_mask_rcnn_fpn_sr_0p5_800_1333_4xdec_coco_3x.json) | | <sub>**MIMDet-ViT-L** | <sub>0.5 | <sub>3x | <sub>[480-800, 1333] w/crop | <sub>54.3 | <sub>48.2 | <sub>349.33M | <sub>[config](configs/mimdet/mimdet_vit_large_mask_rcnn_fpn_sr_0p5_800_1333_4xdec_coco_3x.py) | <sub>[model](https://github.com/hustvl/Storage/releases/download/v1.2.0/mimdet_vit_large_mask_rcnn_fpn_sr_0p5_800_1333_4xdec_coco_3x.pth) / [log](https://github.com/hustvl/Storage/releases/download/v1.2.0/mimdet_vit_large
Excerpt of 9,162 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:92bc51c7efe9bdfb, topic:computer-vision, topic:object-detection, readme:object detection
matched fp:92bc51c7efe9bdfb, topic:transformer