Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Shuguang, Wang, Yuanjing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.01548
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917883194376192
author Wang, Shuguang
Wang, Yuanjing
author_facet Wang, Shuguang
Wang, Yuanjing
contents This paper presents a novel neural network architecture featuring automatic fixation point selection, designed to efficiently address complex tasks with reduced network size and computational overhead. The proposed model consists of: a low-resolution channel that captures low-resolution global features from input images; a high-resolution channel that sequentially extracts localized high-resolution features; and a hybrid encoding module that integrates the features from both channels. A defining characteristic of the hybrid encoding module is the inclusion of a fixation point generator, which dynamically produces fixation points, enabling the high-resolution channel to focus on regions of interest. The fixation points are generated in a task-driven manner, enabling the automatic selection of regions of interest. This approach avoids exhaustive high-resolution analysis of the entire image, maintaining task performance and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01548
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Task-Driven Fixation Network: An Efficient Architecture with Fixation Selection
Wang, Shuguang
Wang, Yuanjing
Computer Vision and Pattern Recognition
This paper presents a novel neural network architecture featuring automatic fixation point selection, designed to efficiently address complex tasks with reduced network size and computational overhead. The proposed model consists of: a low-resolution channel that captures low-resolution global features from input images; a high-resolution channel that sequentially extracts localized high-resolution features; and a hybrid encoding module that integrates the features from both channels. A defining characteristic of the hybrid encoding module is the inclusion of a fixation point generator, which dynamically produces fixation points, enabling the high-resolution channel to focus on regions of interest. The fixation points are generated in a task-driven manner, enabling the automatic selection of regions of interest. This approach avoids exhaustive high-resolution analysis of the entire image, maintaining task performance and computational efficiency.
title Task-Driven Fixation Network: An Efficient Architecture with Fixation Selection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.01548