paper-with-me

Papers

Localizing Objects with Self-Supervised Transformers and no Labels

2021-09-29 · Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon Roburin, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Renaud Marlet, Jean Ponce

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.

📄 PDF Abstract BibTeX arXiv:2109.14279

Code (2)

valeoai/LOST 공식 구현 pytorch
lukemelas/deep-spectral-segmentation pytorch

Tasks

ObjectObject DiscoverySingle-object discoveryWeakly-Supervised Object Localization

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization

2022-09-09 · Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Aydin Sarraf 외

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 Localization

Affinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humans

2023-06-01 · Hossein Adeli, Seoyoung Ahn, Nikolaus Kriegeskorte, Gregory Zelinsky

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 Learning

DADO: A Depth-Attention framework for Object Discovery

2025-10-08 · Federico Gonzalez, Estefania Talavera, Petia Radeva arxiv

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

2024-10-30 · Takuto Yamamoto, Hirosato Akahoshi, Shigeru Kitazawa

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 Prediction

Unsupervised Camouflaged Object Segmentation as Domain Adaptation

2023-08-08 · Yi Zhang, Chengyi Wu

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