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

LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training

About

Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves together belongs together. Building upon this idea, we propose a self-supervised object discovery approach that leverages motion and appearance information to produce high-quality object segmentation masks. Specifically, we redesign the traditional graph cut on images to include motion information in a linear combination with appearance information to produce edge weights. Remarkably, this step produces object segmentation masks comparable to the current state-of-the-art on multiple benchmarks. To further improve performance, we bootstrap a segmentation network trained on these preliminary masks as pseudo-ground truths to learn from its own outputs via self-training. We demonstrate the effectiveness of our approach, named LOCATE, on multiple standard video object segmentation, image saliency detection, and object segmentation benchmarks, achieving results on par with and, in many cases surpassing state-of-the-art methods. We also demonstrate the transferability of our approach to novel domains through a qualitative study on in-the-wild images. Additionally, we present extensive ablation analysis to support our design choices and highlight the contribution of each component of our proposed method.

Silky Singh, Shripad Deshmukh, Mausoom Sarkar, Balaji Krishnamurthy• 2023

Related benchmarks

TaskDatasetResultRank
Unsupervised Video Object SegmentationDAVIS 2016 (val)--
108
Unsupervised Video Object SegmentationSegTrack v2
Jaccard Score79.9
56
Unsupervised Video Object SegmentationDAVIS 2016 (test)
J Mean80.9
50
Single Object Video SegmentationSegTrack v2 (val)
J Mean79.9
27
Unsupervised Video Object SegmentationFBMS-59 (test)
J Score68.8
17
Unsupervised Image Saliency DetectionDUTS 71 (test)
Acc94.4
11
Unsupervised Image Saliency DetectionECSSD 55 (test)
Accuracy93.3
11
Unsupervised Image Saliency DetectionOMRON 84 (test)
Accuracy91.7
10
Unsupervised Object SegmentationCUB 70 (test)
Accuracy95.1
5
Unsupervised Object SegmentationFlowers 44 (test)
Accuracy83.5
3
Showing 10 of 10 rows

Other info

Code

Follow for update