Learning to Observe: Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations
Alan Dolhasz, Carlo Harvey, Ian Williams
Abstract
Many tasks in computer vision are often calibrated and evaluated relative to human perception. In this paper, we propose to directly approximate the perceptual function performed by human observers completing a visual detection task. Specifically, we present a novel methodology for learning to detect image transformations visible to human observers through approximating perceptual thresholds. To do this, we carry out a subjective two-alternative forcedchoice study to estimate perceptual thresholds of human observers detecting local exposure shifts in images. We then leverage transformation equivariant representation learning to overcome issues of limited perceptual data. This representation is then used to train a dense convolutional classifier capable of detecting local suprathreshold exposure shifts -a distortion common to image composites. In this context, our model can approximate perceptual thresholds with an average error of 0.1148 exposure stops between empirical and predicted thresholds. It can also be trained to detect a range of different local transformations.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Related papers
- Self-supervised Transformation Learning for Equivariant RepresentationsJaemyung Yu, Jaehyun Choi, Dong-Jae Lee, Hyeong Gwon Hong et al.NeurIPS 2024 · 10 citations
- Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area ITThomas E. Yerxa, Jenelle Feather, Eero P. Simoncelli, SueYeon ChungNeurIPS 2024 · 12 citations
- Improving neural network representations using human similarity judgmentsLukas Muttenthaler, Lorenz Linhardt, Jonas Dippel, Robert A. Vandermeulen et al.NeurIPS 2023 · 61 citations
- Equivariant Self-Supervised Learning: Encouraging Equivariance in RepresentationsRumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han et al.ICLR 2022 · 54 citations
- TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework Using Self-Supervised Multi-Task LearningLinhao Qu, Shaolei Liu, Manning Wang, Zhijian SongAAAI 2022 · 186 citations
