Ajou University repository

One-Step Pixel-Level Perturbation-Based Saliency Detector
Citations

SCOPUS

0

Citation Export

Publication Year
2021-01-01
Journal
32nd British Machine Vision Conference, BMVC 2021
Publisher
British Machine Vision Association, BMVA
Citation
32nd British Machine Vision Conference, BMVC 2021
Mesh Keyword
Backward propagationFast computationForward propagationIterative OptimizationLocal areasLower memory requirementPerturbation effectPixel levelPropagation stepSaliency map
All Science Classification Codes (ASJC)
Artificial IntelligenceComputer Vision and Pattern Recognition
Abstract
To explain deep neural networks, many perturbation-based saliency methods are studied in the computer vision domain. However, previous perturbation-based saliency methods require iterative optimization steps or multiple forward propagation steps. In this paper, we propose a new perturbation-based saliency that requires only one backward propagation step by approximating the perturbation effect on the output in the local area. We empirically demonstrate that our method shows fast computations and low memory requirements comparable to other most efficient baselines. Furthermore, our method simultaneously considers all possible perturbing directions so as not to misestimate the perturbation effect. Our ablation study shows that considering all possible perturbing directions is crucial to obtain a correct saliency map. Lastly, our method exhibits competitive performance on the benchmarks in evaluating the pixel-level saliency map. Code is available at https://github.com/vinnamkim/OPPSD.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36659
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85174500307&origin=inward
Type
Conference
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Cho, Hyunsouk Image
Cho, Hyunsouk조현석
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.