Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

CVPR 2022

Yangtao Wang¹        Xi Shen^2,3       Xu Hu⁴       Yuan Yuan⁵       James L. Crowley¹       Dominique Vaufreydaz¹

Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 38000 Grenoble, France¹           
Tencent AI Lab²            LIGM (UMR 8049) - Ecole des Ponts, UPE³           
Samsung AI Center, Cambridge⁴            MIT CSAIL⁵           

[Paper]        [GitLab]        [GitHub]               

Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the self-supervised transformer features to discover an object from an image. Visual tokens are viewed as nodes in a weighted graph with edges representing a connectivity score based on the similarity of tokens. Foreground objects can then be segmented using a normalized graph-cut to group self-similar regions. We solve the graph-cut problem using spectral clustering with generalized eigen-decomposition and show that the second smallest eigenvector provides a cutting solution since its absolute value indicates the likelihood that a token belongs to a foreground object.

Despite its simplicity, this approach significantly boosts the performance of unsupervised object discovery: we improve over the recent state of the art LOST by a margin of 6.9%, 8.1%, and 8.1% respectively on the VOC07, VOC12, and COCO20K. The performance can be further improved by adding a second stage class-agnostic detector (CAD). Our proposed method can be easily extended to unsupervised saliency detection and weakly supervised object detection. For unsupervised saliency detection, we improve IoU for 4.9%, 5.2%, 12.9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art. For weakly supervised object detection, we achieve competitive performance on CUB and ImageNet.

	Raw Image		EigenVector Attention		Detection(Red)

	Raw Image		Attention		Detection

	Raw Image		TokenCut		TokenCut + Bilateral Solver

Code and Paper

GitLab	GitLab	Demo	Paper

To cite our paper,

  @inproceedings{wang2022tokencut,
          title={Self-supervised Transformers for Unsupervised Object Discovery using Normalized Cut},
          author={Wang, Yangtao and Shen, Xi and Hu, Shell Xu and Yuan, Yuan and Crowley, James L.
                  and Vaufreydaz, Dominique},
          booktitle={Conference on Computer Vision and Pattern Recognition},
          address = {New Orleans, LA, USA},
          month = {June},
          year={2022}
        }