upcarta
  • Sign In
  • Sign Up
  • Explore
  • Search

Cut and Learn for Unsupervised Object Detection and Instance Segmentation

  • Paper
  • Jan 26, 2023
  • #ComputerScience #Engineering
Rohit Girdhar
@_rohitgirdhar_
(Author)
Ishan Misra
@imisra_
(Author)
arxiv.org
Read on arxiv.org
1 Recommender
1 Mention
We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. We leverage the property of self-supervised models to 'disco... Show More

We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. We leverage the property of self-supervised models to 'discover' objects without supervision and amplify it to train a state-of-the-art localization model without any human labels. CutLER first uses our proposed MaskCut approach to generate coarse masks for multiple objects in an image and then learns a detector on these masks using our robust loss function. We further improve the performance by self-training the model on its predictions. Compared to prior work, CutLER is simpler, compatible with different detection architectures, and detects multiple objects. CutLER is also a zero-shot unsupervised detector and improves detection performance AP50 by over 2.7 times on 11 benchmarks across domains like video frames, paintings, sketches, etc. With finetuning, CutLER serves as a low-shot detector surpassing MoCo-v2 by 7.3% APbox and 6.6% APmask on COCO when training with 5% labels.

Show Less
Recommend
Post
Save
Complete
Collect
Mentions
See All
Akshay ๐Ÿš€ @akshay_pachaar ยท Mar 1, 2023
  • Post
  • From Twitter
Unsupervised Object detection & instance segmentation! ๐Ÿ”ฅ This is a very interesting read. Check this out ๐Ÿ‘‡
  • upcarta ยฉ2025
  • Home
  • About
  • Terms
  • Privacy
  • Cookies
  • @upcarta