Tag: #cosine estimator

Congratulations to our labmates: Joshua Peeples, Connor McCurley, Sarah Walker,  Dylan Stewart and Alina Zare! Their paper, “LEARNABLE ADAPTIVE COSINE ESTIMATOR (LACE) FOR IMAGE CLASSIFICATION “, was recently accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022. In the paper, the authors propose a new loss to improve feature discriminability and 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 […]