HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping
Preprint
Abstract
Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised transformer features. However, their scopes only build upon patch-level features within an image, neglecting region/image-level and cross-image relationships at a broader scale. Moreover, these methods cannot differentiate various semantics from multiple instances. To address these problems, we introduce Hierarchical mErging framework via contrAstive grouPing (HEAP). Specifically, a novel lightweight head with cross-attention mechanism is designed to adaptively group intra-image patches into semantically coherent regions based on correlation among self-supervised features. Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images. Also, an image-level contrastive loss is present to push foreground and background representations apart, with which foreground objects and background are accordingly discovered. HEAP facilitates efficient hierarchical image decomposition, which contributes to more accurate object discovery while also enabling differentiation among objects of various classes. Extensive experimental results on semantic segmentation retrieval, unsupervised object discovery, and saliency detection tasks demonstrate that HEAP achieves state-of-the-art performance.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation2023
- Unsupervised object discovery and co-localization by deep descriptor transformationPattern Recognition, 2019
- Hierarchical Image Saliency Detection on Extended CSSDIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Finding and evaluating community structure in networksPhysical Review E, 2004