On Human-like Biases in Convolutional Neural Networks for the Perception of Slant from Texture

Author:

Wang Yuanhao1ORCID,Zhang Qian1ORCID,Aubuchon Celine2ORCID,Kemp Jovan2ORCID,Domini Fulvio2ORCID,Tompkin James1ORCID

Affiliation:

1. Brown University Department of Computer Science, USA

2. Brown University Department of Cognitive, Linguistic, and Psychological Sciences, USA

Abstract

Depth estimation is fundamental to 3D perception, and humans are known to have biased estimates of depth. This study investigates whether convolutional neural networks (CNNs) can be biased when predicting the sign of curvature and depth of surfaces of textured surfaces under different viewing conditions (field of view) and surface parameters (slant and texture irregularity). This hypothesis is drawn from the idea that texture gradients described by local neighborhoods—a cue identified in human vision literature—are also representable within convolutional neural networks. To this end, we trained both unsupervised and supervised CNN models on the renderings of slanted surfaces with random Polka dot patterns and analyzed their internal latent representations. The results show that the unsupervised models have similar prediction biases as humans across all experiments, while supervised CNN models do not exhibit similar biases. The latent spaces of the unsupervised models can be linearly separated into axes representing field of view and optical slant. For supervised models, this ability varies substantially with model architecture and the kind of supervision (continuous slant vs. sign of slant). Even though this study says nothing of any shared mechanism, these findings suggest that unsupervised CNN models can share similar predictions to the human visual system. Code: github.com/brownvc/Slant-CNN-Biases.

Funder

NSF

NIH

Publisher

Association for Computing Machinery (ACM)

Subject

Experimental and Cognitive Psychology,General Computer Science,Theoretical Computer Science

Reference28 articles.

1. Explicit and implicit depth-cue integration: Evidence of systematic biases with real objects

2. 3-D structure perceived from dynamic information: a new theory

3. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness;Geirhos Robert;arXiv preprint arXiv:1811.12231,2018

4. James J. Gibson. 1950a. The Perception of the Visual World . (1950).

5. The Perception of Visual Surfaces

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3