Debiased Novel Category Discovering and Localization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Feng, Juexiao, Yang, Yuhong, Xie, Yanchun, Li, Yaqian, Guo, Yandong, Guo, Yuchen, He, Yuwei, Xiang, Liuyu, Ding, Guiguang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913247752355840
author Feng, Juexiao
Yang, Yuhong
Xie, Yanchun
Li, Yaqian
Guo, Yandong
Guo, Yuchen
He, Yuwei
Xiang, Liuyu
Ding, Guiguang
author_facet Feng, Juexiao
Yang, Yuhong
Xie, Yanchun
Li, Yaqian
Guo, Yandong
Guo, Yuchen
He, Yuwei
Xiang, Liuyu
Ding, Guiguang
contents In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often identified as background or incorrectly classified as pre-defined categories by the detectors. In this paper, we focus on the challenging problem of Novel Class Discovery and Localization (NCDL), aiming to train detectors that can detect the categories present in the training data, while also actively discover, localize, and cluster new categories. We analyze existing NCDL methods and identify the core issue: object detectors tend to be biased towards seen objects, and this leads to the neglect of unseen targets. To address this issue, we first propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN in a complementary manner. Additionally, we suggest to improve the representation network through semi-supervised contrastive learning by leveraging unlabeled data. Finally, we adopt a simple and efficient mini-batch K-means clustering method for novel class discovery. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods, establishing a new state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Debiased Novel Category Discovering and Localization
Feng, Juexiao
Yang, Yuhong
Xie, Yanchun
Li, Yaqian
Guo, Yandong
Guo, Yuchen
He, Yuwei
Xiang, Liuyu
Ding, Guiguang
Computer Vision and Pattern Recognition
In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often identified as background or incorrectly classified as pre-defined categories by the detectors. In this paper, we focus on the challenging problem of Novel Class Discovery and Localization (NCDL), aiming to train detectors that can detect the categories present in the training data, while also actively discover, localize, and cluster new categories. We analyze existing NCDL methods and identify the core issue: object detectors tend to be biased towards seen objects, and this leads to the neglect of unseen targets. To address this issue, we first propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN in a complementary manner. Additionally, we suggest to improve the representation network through semi-supervised contrastive learning by leveraging unlabeled data. Finally, we adopt a simple and efficient mini-batch K-means clustering method for novel class discovery. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods, establishing a new state-of-the-art.
title Debiased Novel Category Discovering and Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.18821