Maximum-Entropy Fine-Grained Classification
This addresses the problem of fine-grained classification for computer vision applications, offering a robust method that is incremental in improving existing approaches.
The paper tackles fine-grained visual classification by proposing a maximum-entropy training routine for convolutional neural networks, achieving state-of-the-art performance across various tasks with robustness to hyperparameters, data amount, and label noise.
Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data. Utilizing this notion of small visual diversity, we revisit Maximum-Entropy learning in the context of fine-grained classification, and provide a training routine that maximizes the entropy of the output probability distribution for training convolutional neural networks on FGVC tasks. We provide a theoretical as well as empirical justification of our approach, and achieve state-of-the-art performance across a variety of classification tasks in FGVC, that can potentially be extended to any fine-tuning task. Our method is robust to different hyperparameter values, amount of training data and amount of training label noise and can hence be a valuable tool in many similar problems.