Detect and segment unknown objects with unsupervised learning using graph partitioning with CutLER
--
Detect and segment unknown objects with unsupervised learning using graph partitioning with CutLER
Cut and Learn for Unsupervised Object Detection and Instance Segmentation
arXiv paper abstract https://arxiv.org/abs/2301.11320
arXiv PDF paper https://arxiv.org/pdf/2301.11320.pdf
GitHub https://github.com/facebookresearch/cutler
… propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models.
… 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 … proposed MaskCut approach to generate coarse masks for multiple objects in an image and then learns a detector on these masks
… 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 … 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 …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
