L*ReLU: Piece-wise Linear Activation Functions for Deep Fine-grained Visual Categorization
This addresses the need for better activation functions in deep learning for tasks requiring subtle detail discrimination, but it is incremental as it builds on existing ReLU-based methods.
The paper tackles the problem of improving classification accuracy in fine-grained visual categorization by proposing L*ReLU, a piece-wise linear activation function, and shows it achieves superior results on seven benchmark datasets.
Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing in complexity and difficulty, existing solutions mostly build on the same architectural decisions. This also applies to the selection of activation functions (AFs), where most approaches build on Rectified Linear Units (ReLUs). In this paper, however, we show that the choice of a proper AF has a significant impact on the classification accuracy, in particular, if fine, subtle details are of relevance. Therefore, we propose to model the degree of absence and the presence of features via the AF by using piece-wise linear functions, which we refer to as L*ReLU. In this way, we can ensure the required properties, while still inheriting the benefits in terms of computational efficiency from ReLUs. We demonstrate our approach for the task of Fine-grained Visual Categorization (FGVC), running experiments on seven different benchmark datasets. The results do not only demonstrate superior results but also that for different tasks, having different characteristics, different AFs are selected.