Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

About

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.

Yangtao Wang, Xi Shen, Shell Hu, Yuan Yuan, James Crowley, Dominique Vaufreydaz• 2022

Related benchmarks

TaskDatasetResultRank
Salient Object DetectionDUTS (test)--
302
Salient Object DetectionECSSD--
202
Object LocalizationPASCAL VOC 2012 (trainval)
CorLoc72.1
51
Salient Object DetectionECSSD 1,000 images (test)--
48
Saliency DetectionDUT-OMRON 29 (test)
IoU61.8
38
Unsupervised single object discoveryVOC 2007 (test)
CorLoc71.4
34
Unsupervised single object discoveryVOC 2012 (test)
CorLoc75.3
34
Unsupervised single object discoveryCOCO20K 2014 (train)
CorLoc62.6
33
Single-object discoveryPASCAL VOC 2007 (trainval)
CorLoc71.4
26
RGB saliency detectionECSSD--
25
Showing 10 of 23 rows

Other info

Code

Follow for update