Localizing Objects with Self-Supervised Transformers and no Labels
Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a self-supervised manner. Our method, LOST, does not require any external object proposal nor any exploration of the image collection; it operates on a single image. Yet, we outperform state-of-the-art object discovery methods by up to 8 CorLoc points on PASCAL VOC 2012. We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points. Moreover, we show promising results on the unsupervised object discovery task. The code to reproduce our results can be found at https://github.com/valeoai/LOST.
Code (2)
Tasks
ObjectObject DiscoverySingle-object discoveryWeakly-Supervised Object LocalizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization
Drones are employed in a growing number of visual recognition applications. A recent development in cell tower inspection is drone-based asset surveillance, where the autonomous flight of a drone is guided by localizing …
ObjectObject LocalizationWeakly-Supervised Object LocalizationAffinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humans
The spreading of attention has been proposed as a mechanism for how humans group features to segment objects. However, such a mechanism has not yet been implemented and tested in naturalistic images. Here, we leverage th…
ObjectRepresentation LearningDADO: A Depth-Attention framework for Object Discovery
Unsupervised object discovery, the task of identifying and localizing objects in images without human-annotated labels, remains a significant challenge and a growing focus in computer vision. In this work, we introduce a…
Emergence of Human-Like Attention in Self-Supervised Vision Transformers: an eye-tracking study
Many models of visual attention have been proposed so far. Traditional bottom-up models, like saliency models, fail to replicate human gaze patterns, and deep gaze prediction models lack biological plausibility due to th…
Gaze PredictionUnsupervised Camouflaged Object Segmentation as Domain Adaptation
Deep learning for unsupervised image segmentation remains challenging due to the absence of human labels. The common idea is to train a segmentation head, with the supervision of pixel-wise pseudo-labels generated based …
AttributeCamouflaged Object SegmentationDomain AdaptationImage Segmentation+5