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 (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.

Accepted to WACV 2022; 14 pages (including appendix), 3 figures

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• A Simple Framework for Contrastive Learning of Visual Representations
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Deep Learning Face Representation by Joint Identification-Verification
• A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples
• A survey on Semi-, Self- and Unsupervised Learning for Image Classification
• Whitening Sentence Representations for Better Semantics and Faster Retrieval
• Fixing the train-test resolution discrepancy: FixEfficientNet
• Natural Neural Networks
• Whitening for Self-Supervised Representation Learning
• Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classification