ACE: Adaptive Confusion Energy for Natural World Data Distribution
This addresses the challenge of handling imbalanced and fine-grained data in real-world classification tasks, representing an incremental improvement over existing methods that often focus on only one aspect.
The paper tackles the problem of fine-grained and long-tailed data distributions in natural world classification by introducing Adaptive Confusion Energy (ACE), a batch-wise regularization method that improves training effectiveness and achieves competitive performance on datasets like CUB, CAR, AIR, ImageNet-LT, CUB-LT, and iNaturalist.
With the development of deep learning, standard classification problems have achieved good results. However, conventional classification problems are often too idealistic. Most data in the natural world usually have imbalanced distribution and fine-grained characteristics. Recently, many state-of-the-art approaches tend to focus on one or another separately, but rarely on both. In this paper, we introduce a novel and adaptive batch-wise regularization based on the proposed Adaptive Confusion Energy (ACE) to flexibly address the nature world distribution, which usually involves fine-grained and long-tailed properties at the same time. ACE increases the difficulty of the training process and further alleviates the overfitting problem. Through the datasets with the technical issue in fine-grained (CUB, CAR, AIR) and long-tailed (ImageNet-LT), or comprehensive issues (CUB-LT, iNaturalist), the result shows that the ACE is not only competitive to some state-of-the-art on performance but also demonstrates the effectiveness of training.