Learnable Adaptive Cosine Estimator (LACE) for Image Classification

less than 1 minute read

Abstract:

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.

“PDF IEEE

Citation:

J. Peeples, C. H. McCurley, S. Walker, D. Stewart, and A. Zare. "Learnable Adaptive Cosine Estimator (LACE) for Image Classification," in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3479-3489, 2022.
@InProceedings{Peeples2022LACE,
author    = {J. Peeples and C. H. McCurley and S. Walker and D. Stewart and A. Zare},
title     = {Learnable Adaptive Cosine Estimator (LACE) for Image Classification},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month     = {January},
year      = {2022},
pages     = {3479-3489}
}