mlsanityData to 14 Oct 2026

Learnable Adaptive Cosine Estimator (LACE) for Image Classification

arXiv 2110.05324 ↗First posted 11 Oct 2021cs.CV cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 67 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

36 of 67 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  7. 2014Going Deeper with Convolutionscited by 4,241
  8. 2016Wide Residual Networkscited by 3,070
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  10. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  11. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  12. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
24 more
  1. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  2. 2014Deep metric learning using Triplet networkcited by 422
  3. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  4. 2020Whitening for Self-Supervised Representation Learningcited by 279
  5. 2019A Survey of the Recent Architectures of Deep Convolutional Neural Networkscited by 213
  6. 2019Fixing the train-test resolution discrepancycited by 209
  7. 2021Whitening Sentence Representations for Better Semantics and Faster Retrievalcited by 202
  8. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 190
  9. 2014Deep Learning Face Representation by Joint Identification-Verificationcited by 162
  10. 2019Iterative Normalization: Beyond Standardization towards Efficient Whiteningcited by 92
  11. 2018Decorrelated Batch Normalizationcited by 83
  12. 2019AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representationscited by 83
  13. 2018ArcFace: Additive Angular Margin Loss for Deep Face Recognitioncited by 56
  14. 2020A survey on Semi-, Self- and Unsupervised Learning for Image Classificationcited by 55
  15. 2015Natural Neural Networkscited by 44
  16. 2018Deep Texture Manifold for Ground Terrain Recognitioncited by 32
  17. 2020Fixing the train-test resolution discrepancy: FixEfficientNetcited by 31
  18. 2017Contrastive-center loss for deep neural networkscited by 20
  19. 2015Sparsifying Neural Network Connections for Face Recognitioncited by 15
  20. 2020AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classificationcited by 14
  21. 2021Stochastic Whitening Batch Normalizationcited by 9
  22. 2018Angular Softmax Loss for End-to-end Speaker Verificationcited by 7
  23. 2020Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classificationcited by 2
  24. 2019Multi-Target Multiple Instance Learning for Hyperspectral Target Detectioncited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 1.

2 papers.

  1. 2023Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognitioncited by 0
  2. 2025Patch distribution modeling framework adaptive cosine estimator (PaDiM-ACE) for anomaly detection and localization in synthetic aperture radar imagerycited by 0