Learnable Adaptive Cosine Estimator (LACE) for Image Classification
This work addresses the need for better loss functions in image classification, offering a novel method that could benefit researchers and practitioners in computer vision, though it appears incremental as it builds on existing adaptive cosine estimator concepts.
The authors tackled the problem of improving feature discriminability and classification performance in image classification by proposing a new loss function called Learnable Adaptive Cosine Estimator (LACE), which transforms data into a whitened space to enhance inter-class separability and intra-class compactness, showing it can serve as a viable alternative to cross entropy and angular softmax approaches.
In this work, we propose a new loss to improve feature discriminability and classification performance. Motivated by the adaptive cosine/coherence estimator (ACE), our proposed method incorporates angular information that is inherently learned by artificial neural networks. Our learnable ACE (LACE) transforms the data into a new "whitened" space that improves the inter-class separability and intra-class compactness. We compare our LACE to alternative state-of-the art softmax-based and feature regularization approaches. Our results show that the proposed method can serve as a viable alternative to cross entropy and angular softmax approaches. Our code is publicly available: https://github.com/GatorSense/LACE.