Exploring Color Invariance through Image-Level Ensemble Learning

1 code implementation • 19 Jan 2024 • Yunpeng Gong, Jiaquan Li, Lifei Chen, Min Jiang

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.

Data Augmentation Ensemble Learning +2