Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization
Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks, especially in challenging conditions such as cluttered images. However, little is known about the exact computational role of recurrent information flow in these conditions. Here we test RNNs trained for object categorization on the hypothesis that recurrence iteratively aids object categorization via the communication of category-orthogonal auxiliary variables (the location, orientation, and scale of the object). Using diagnostic linear readouts, we find that: (a) information about auxiliary variables increases across time in all network layers, (b) this information is indeed present in the recurrent information flow, and (c) its manipulation significantly affects task performance. These observations confirm the hypothesis that category-orthogonal auxiliary variable information is conveyed through recurrent connectivity and is used to optimize category inference in cluttered environments.
Code (1)
Tasks
DiagnosticObjectObject CategorizationSimilar Papers 제목 키워드 기반
MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training. While these methods achieve reasonable improvements in performance, they typically perform categor…
Domain Adaptationobject-detectionObject DetectionMultimodal Query-guided Object Localization
Consider a scenario in one-shot query-guided object localization where neither an image of the object nor the object category name is available as a query. In such a scenario, a hand-drawn sketch of the object could be a…
ObjectObject LocalizationRegion ProposalRCGNet: RGB-based Category-Level 6D Object Pose Estimation with Geometric Guidance
While most current RGB-D-based category-level object pose estimation methods achieve strong performance, they face significant challenges in scenes lacking depth information. In this paper, we propose a novel category-le…
Pose EstimationCSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection
Domain Adaptive Object Detection (DAOD) aims to improve the detection performance of target domains by minimizing the feature distribution between the source and target domain. Recent approaches usually align such di…
Objectobject-detectionObject DetectionReference-based Category Discovery: Unsupervised Object Detection with Category Awareness
Traditional one-shot detection methods have addressed the closed-set problem in object detection, but the high cost of data annotation remains a critical challenge. General unsupervised methods generate pseudo boxes with…
Object Detection