CONDA: Condensed Deep Association Learning for Co-Salient Object Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Long, Liu, Nian, Zhang, Dingwen, Li, Zhongyu, Khan, Salman, Anwer, Rao, Cholakkal, Hisham, Han, Junwei, Khan, Fahad Shahbaz
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917799757086720
author Li, Long
Liu, Nian
Zhang, Dingwen
Li, Zhongyu
Khan, Salman
Anwer, Rao
Cholakkal, Hisham
Han, Junwei
Khan, Fahad Shahbaz
author_facet Li, Long
Liu, Nian
Zhang, Dingwen
Li, Zhongyu
Khan, Salman
Anwer, Rao
Cholakkal, Hisham
Han, Junwei
Khan, Fahad Shahbaz
contents Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.
format Preprint
id arxiv_https___arxiv_org_abs_2409_01021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CONDA: Condensed Deep Association Learning for Co-Salient Object Detection
Li, Long
Liu, Nian
Zhang, Dingwen
Li, Zhongyu
Khan, Salman
Anwer, Rao
Cholakkal, Hisham
Han, Junwei
Khan, Fahad Shahbaz
Computer Vision and Pattern Recognition
Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.
title CONDA: Condensed Deep Association Learning for Co-Salient Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.01021