Exploring Color Invariance through Image-Level Ensemble Learning Article Swipe

MAKE IMPACT

Yunpeng Gong , Jiaquan Li , Lifei Chen , Min Jiang · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2401.10512

In the field of computer vision, the persistent presence of color bias, resulting from fluctuations in real-world lighting and camera conditions, presents a substantial challenge to the robustness of models. This issue is particularly pronounced in complex wide-area surveillance scenarios, such as person re-identification and industrial dust segmentation, where models often experience a decline in performance due to overfitting on color information during training, given the presence of environmental variations. Consequently, there is a need to effectively adapt models to cope with the complexities of camera conditions. To address this challenge, this study introduces a learning strategy named Random Color Erasing, which draws inspiration from ensemble learning. This strategy selectively erases partial or complete color information in the training data without disrupting the original image structure, thereby achieving a balanced weighting of color features and other features within the neural network. This approach mitigates the risk of overfitting and enhances the model's ability to handle color variation, thereby improving its overall robustness. The approach we propose serves as an ensemble learning strategy, characterized by robust interpretability. A comprehensive analysis of this methodology is presented in this paper. Across various tasks such as person re-identification and semantic segmentation, our approach consistently improves strong baseline methods. Notably, in comparison to existing methods that prioritize color robustness, our strategy significantly enhances performance in cross-domain scenarios. The code available at \url{https://github.com/layumi/Person\_reID\_baseline\_pytorch/blob/master/random\_erasing.py} or \url{https://github.com/finger-monkey/Data-Augmentation}.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2401.10512

PDF

https://arxiv.org/pdf/2401.10512

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4391124025

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4391124025

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2401.10512

Digital Object Identifier

Title

Exploring Color Invariance through Image-Level Ensemble Learning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2024

Year of publication

Publication date

2024-01-19

Full publication date if available

Authors

Yunpeng Gong, Jiaquan Li, Lifei Chen, Min Jiang

List of authors in order

Landing page

https://arxiv.org/abs/2401.10512

Publisher landing page

PDF URL

https://arxiv.org/pdf/2401.10512

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2401.10512

Direct OA link when available

Concepts

Overfitting, Computer science, Robustness (evolution), Artificial intelligence, Interpretability, Ensemble learning, Machine learning, Random forest, Weighting, Deep learning, Segmentation, Ensemble forecasting, Code (set theory), Pattern recognition (psychology), Computer vision, Artificial neural network, Medicine, Programming language, Gene, Biochemistry, Radiology, Set (abstract data type), Chemistry

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload