ColorSense: A Study on Color Vision in Machine Visual Recognition
- URL: http://arxiv.org/abs/2212.08650v2
- Date: Tue, 01 Oct 2024 21:58:46 GMT
- Title: ColorSense: A Study on Color Vision in Machine Visual Recognition
- Authors: Ming-Chang Chiu, Yingfei Wang, Derrick Eui Gyu Kim, Pin-Yu Chen, Xuezhe Ma,
- Abstract summary: We collect 110,000 non-trivial human annotations of foreground and background color labels from visual recognition benchmarks.
We validate the use of our datasets by demonstrating that the level of color discrimination has a dominating effect on the performance of machine perception models.
Our findings suggest that object recognition tasks such as classification and localization are susceptible to color vision bias.
- Score: 57.916512479603064
- License:
- Abstract: Color vision is essential for human visual perception, but its impact on machine perception is still underexplored. There has been an intensified demand for understanding its role in machine perception for safety-critical tasks such as assistive driving and surgery but lacking suitable datasets. To fill this gap, we curate multipurpose datasets ColorSense, by collecting 110,000 non-trivial human annotations of foreground and background color labels from popular visual recognition benchmarks. To investigate the impact of color vision on machine perception, we assign each image a color discrimination level based on its dominant foreground and background colors and use it to study the impact of color vision on machine perception. We validate the use of our datasets by demonstrating that the level of color discrimination has a dominating effect on the performance of mainstream machine perception models. Specifically, we examine the perception ability of machine vision by considering key factors such as model architecture, training objective, model size, training data, and task complexity. Furthermore, to investigate how color and environmental factors affect the robustness of visual recognition in machine perception, we integrate our ColorSense datasets with image corruptions and perform a more comprehensive visual perception evaluation. Our findings suggest that object recognition tasks such as classification and localization are susceptible to color vision bias, especially for high-stakes cases such as vehicle classes, and advanced mitigation techniques such as data augmentation and so on only give marginal improvement. Our analyses highlight the need for new approaches toward the performance evaluation of machine perception models in real-world applications. Lastly, we present various potential applications of ColorSense such as studying spurious correlations.
Related papers
- Impact of Iris Pigmentation on Performance Bias in Visible Iris Verification Systems: A Comparative Study [6.639785884921617]
We investigate the impact of iris pigmentation on the efficacy of biometric recognition systems, focusing on a comparative analysis of blue and dark irises.
Our results indicate that iris recognition systems generally exhibit higher accuracy for blue irises compared to dark irises.
Our analysis identifies inherent biases in recognition performance related to iris color and cross-device variability.
arXiv Detail & Related papers (2024-11-13T10:15:27Z) - When Does Perceptual Alignment Benefit Vision Representations? [76.32336818860965]
We investigate how aligning vision model representations to human perceptual judgments impacts their usability.
We find that aligning models to perceptual judgments yields representations that improve upon the original backbones across many downstream tasks.
Our results suggest that injecting an inductive bias about human perceptual knowledge into vision models can contribute to better representations.
arXiv Detail & Related papers (2024-10-14T17:59:58Z) - What Makes Pre-Trained Visual Representations Successful for Robust
Manipulation? [57.92924256181857]
We find that visual representations designed for manipulation and control tasks do not necessarily generalize under subtle changes in lighting and scene texture.
We find that emergent segmentation ability is a strong predictor of out-of-distribution generalization among ViT models.
arXiv Detail & Related papers (2023-11-03T18:09:08Z) - FACET: Fairness in Computer Vision Evaluation Benchmark [21.862644380063756]
Computer vision models have known performance disparities across attributes such as gender and skin tone.
We present a new benchmark named FACET (FAirness in Computer Vision EvaluaTion)
FACET is a large, publicly available evaluation set of 32k images for some of the most common vision tasks.
arXiv Detail & Related papers (2023-08-31T17:59:48Z) - The Influences of Color and Shape Features in Visual Contrastive
Learning [0.0]
This paper investigates the influences of individual image features (e.g., color and shape) to model performance remain ambiguous.
Experimental results show that compared with supervised representations, contrastive representations tend to cluster with objects of similar color.
arXiv Detail & Related papers (2023-01-29T15:10:14Z) - Peripheral Vision Transformer [52.55309200601883]
We take a biologically inspired approach and explore to model peripheral vision in deep neural networks for visual recognition.
We propose to incorporate peripheral position encoding to the multi-head self-attention layers to let the network learn to partition the visual field into diverse peripheral regions given training data.
We evaluate the proposed network, dubbed PerViT, on the large-scale ImageNet dataset and systematically investigate the inner workings of the model for machine perception.
arXiv Detail & Related papers (2022-06-14T12:47:47Z) - Fairness Indicators for Systematic Assessments of Visual Feature
Extractors [21.141633753573764]
We propose three fairness indicators, which aim at quantifying harms and biases of visual systems.
Our indicators use existing publicly available datasets collected for fairness evaluations.
These indicators are not intended to be a substitute for a thorough analysis of the broader impact of the new computer vision technologies.
arXiv Detail & Related papers (2022-02-15T17:45:33Z) - Exploring Visual Engagement Signals for Representation Learning [56.962033268934015]
We present VisE, a weakly supervised learning approach, which maps social images to pseudo labels derived by clustered engagement signals.
We then study how models trained in this way benefit subjective downstream computer vision tasks such as emotion recognition or political bias detection.
arXiv Detail & Related papers (2021-04-15T20:50:40Z) - Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units
and a Unified Framework [83.21732533130846]
The paper focuses on large in-the-wild databases, i.e., Aff-Wild and Aff-Wild2.
It presents the design of two classes of deep neural networks trained with these databases.
A novel multi-task and holistic framework is presented which is able to jointly learn and effectively generalize and perform affect recognition.
arXiv Detail & Related papers (2021-03-29T17:36:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.