Learnable Adaptive Cosine Estimator (LACE) for Image Classification

Abstract:

In this work, we propose a new loss to improve feature discriminability and classification performance. Motivated by the adaptive cosine/coherence estimator [42] (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.

Links:

Citation:

J. Peeples, C. McCurley, S. Walker, D. Stewart, A. Zare, "Learnable Adaptive Cosine Estimator (LACE) for Image Classification." in "IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)", 2022.
@article {peeples2021learnable,
author={Joshua Peeples and Connor McCurley and Sarah Walker and Dylan Stewart and Alina Zare},
eprint={2110.05324},
archivePrefix={arXiv},
primaryClass={cs.CV}
year = {2022},