通过图像级集成学习探索颜色不变性
Exploring Color Invariance through Image-Level Ensemble Learning
AI总结：
针对光照与相机变化导致的颜色偏差和过拟合问题，提出图像级 Random Color Erasing 集成学习策略，在行人重识别与分割等任务及跨域场景中提升基线鲁棒性。
摘要：
在计算机视觉领域，由真实世界光照和相机条件波动所导致的颜色偏差持续存在，对模型的鲁棒性构成了重大挑战。这一问题在复杂的广域监控场景中尤为突出，例如行人重识别和工业粉尘分割；在这些场景中，由于环境变化的存在，模型在训练期间往往会因过拟合颜色信息而出现性能下降。因此，需要有效地调整模型，以应对复杂的相机条件。为应对这一挑战，本研究提出了一种名为 Random Color Erasing（随机颜色擦除）的学习策略，其灵感来源于集成学习。该策略在不破坏原始图像结构的情况下，有选择地擦除训练数据中的部分或全部颜色信息，从而在神经网络内实现颜色特征与其他特征的均衡加权。该方法降低了过拟合风险，并增强了模型处理颜色变化的能力，进而提升其整体鲁棒性。我们提出的方法作为一种集成学习策略，具有较强的可解释性。本文对该方法进行了全面分析。在行人重识别和语义分割等多种任务中，我们的方法持续改进了强基线方法。值得注意的是，与现有优先考虑颜色鲁棒性的方法相比，我们的策略显著提升了跨域场景下的性能。代码可在 https://github.com/layumi/Person_reID_baseline_pytorch/blob/master/random_erasing.py 或 https://github.com/finger-monkey/Data-Augmentation 获取。
英文摘要：
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}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
