English

How saccadic vision might help with theinterpretability of deep networks

Computer Vision and Pattern Recognition 2021-05-28 v1 Artificial Intelligence
Authors: Iana Sereda , Grigory Osipov
View on arXiv ↗ PDF ↗

Abstract

We describe how some problems (interpretability,lack of object-orientedness) of modern deep networks potentiallycould be solved by adapting a biologically plausible saccadicmechanism of perception. A sketch of such a saccadic visionmodel is proposed. Proof of concept experimental results areprovided to support the proposed approach.

Keywords

saccadic vision deep networks interpretability object-orientedness biological plausibility

Cite

@article{arxiv.2105.13264,
  title  = {How saccadic vision might help with theinterpretability of deep networks},
  author = {Iana Sereda and Grigory Osipov},
  journal= {arXiv preprint arXiv:2105.13264},
  year   = {2021}
}

Related papers

View all related →
Computer Vision and Pattern Recognition · Computer Science
Saccade Mechanisms for Image Classification, Object Detection and Tracking
Saurabh Farkya, Zachary Daniels, Aswin Nadamuni Raghavan, David Zhang +1
2022-06-13
Computer Vision and Pattern Recognition · Computer Science
A Disentangling Invertible Interpretation Network for Explaining Latent Representations
Patrick Esser, Robin Rombach, Björn Ommer
2020-04-29
Machine Learning · Computer Science
Open Problems in Mechanistic Interpretability
Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey +25
2025-01-29
Machine Learning · Computer Science
A Survey on Neural Network Interpretability
Yu Zhang, Peter Tiňo, Aleš Leonardis, Ke Tang
2022-02-01
Computer Vision and Pattern Recognition · Computer Science
Network Dissection: Quantifying Interpretability of Deep Visual Representations
David Bau, Bolei Zhou, Aditya Khosla, Aude Oliva +1
2017-04-20
Machine Learning · Computer Science
Assessing the Reliability of Visual Explanations of Deep Models with Adversarial Perturbations
Dan Valle, Tiago Pimentel, Adriano Veloso
2020-04-24
Computer Vision and Pattern Recognition · Computer Science
Visual Interpretability for Deep Learning: a Survey
Quanshi Zhang, Song-Chun Zhu
2018-02-08
Computer Vision and Pattern Recognition · Computer Science
Interpreting Deep Visual Representations via Network Dissection
Bolei Zhou, David Bau, Aude Oliva, Antonio Torralba
2018-06-27
Machine Learning · Computer Science
Methods for Interpreting and Understanding Deep Neural Networks
Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller
2017-11-15
Machine Learning · Computer Science
Deep Interpretable Models of Theory of Mind
Ini Oguntola, Dana Hughes, Katia Sycara
2021-07-14
Computer Vision and Pattern Recognition · Computer Science
Improving Interpretability of Deep Neural Networks with Semantic Information
Yinpeng Dong, Hang Su, Jun Zhu, Bo Zhang
2017-03-31
Computer Vision and Pattern Recognition · Computer Science
Semantic Network Interpretation
Pei Guo, Ryan Farrell
2021-11-22
Artificial Intelligence · Computer Science
Human-Understandable Decision Making for Visual Recognition
Xiaowei Zhou, Jie Yin, Ivor Tsang, Chen Wang
2021-03-08
Machine Learning · Computer Science
Explaining Deep Neural Networks by Leveraging Intrinsic Methods
Biagio La Rosa
2024-07-18
Machine Learning · Computer Science
Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond
Xuhong Li, Haoyi Xiong, Xingjian Li, Xuanyu Wu +4
2022-07-18
Computer Vision and Pattern Recognition · Computer Science
Enhancing Interpretability for Vision Models via Shapley Value Optimization
Kanglong Fan, Yunqiao Yang, Chen Ma
2025-12-17
Computer Vision and Pattern Recognition · Computer Science
Interpretability Beyond Classification Output: Semantic Bottleneck Networks
Max Losch, Mario Fritz, Bernt Schiele
2019-07-30
Computer Vision and Pattern Recognition · Computer Science
Towards Interpretable Deep Networks for Monocular Depth Estimation
Zunzhi You, Yi-Hsuan Tsai, Wei-Chen Chiu, Guanbin Li
2021-08-12
Machine Learning · Computer Science
Generating Interpretable Networks using Hypernetworks
Isaac Liao, Ziming Liu, Max Tegmark
2023-12-07
Computer Vision and Pattern Recognition · Computer Science
Interpretable Mammographic Image Classification using Case-Based Reasoning and Deep Learning
Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao, Chaofan Chen +3
2021-10-06
Machine Learning · Computer Science
Discovering interpretable models of scientific image data with deep learning
Christopher J. Soelistyo, Alan R. Lowe
2024-02-06
Computer Vision and Pattern Recognition · Computer Science
Perception Visualization: Seeing Through the Eyes of a DNN
Loris Giulivi, Mark James Carman, Giacomo Boracchi
2022-04-22
Computer Vision and Pattern Recognition · Computer Science
Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models
Matthew Kowal, Richard P. Wildes, Konstantinos G. Derpanis
2024-04-11
Computer Vision and Pattern Recognition · Computer Science
Towards Visually Explaining Video Understanding Networks with Perturbation
Zhenqiang Li, Weimin Wang, Zuoyue Li, Yifei Huang +1
2020-11-10
Machine Learning · Computer Science
Optimal Explanations of Linear Models
Dimitris Bertsimas, Arthur Delarue, Patrick Jaillet, Sebastien Martin
2019-07-11