Cam-softmax for discriminative deep feature learning

Tamas Suveges, Stephen McKenna (Lead / Corresponding author)

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)
92 Downloads (Pure)


Deep convolutional neural networks are widely used to learn feature spaces for image classification tasks. We propose cam-softmax, a generalisation of the final layer activations and softmax function, that encourages deep feature spaces to exhibit high intra-class compactness and high inter-class separability. We provide an algorithm to automatically adapt the method’s main hyperparameter so that it gradually diverges from the standard activations and softmax method during training. We report experiments using CASIA-Webface, LFW, and YTF face datasets demonstrating that cam-softmax leads to representations well suited to open-set face recognition and face pair matching. Furthermore, we provide empirical evidence that cam-softmax provides some robustness to class labelling errors in training data, making it of potential use for deep learning from large datasets with poorly verified labels .
Original languageEnglish
Title of host publicationProceedings of the 25th International Conference on Pattern Recognition
Place of PublicationMilan
Number of pages7
ISBN (Electronic)9781728188089
ISBN (Print)9781728188089
Publication statusPublished - 5 May 2021
Event25th International Conference on Pattern Recognition - Milan, Italy
Duration: 15 Jan 2021 → …

Publication series

ISSN (Print)1051-4651


Conference25th International Conference on Pattern Recognition
Period15/01/21 → …
Internet address


  • Training
  • Deep learning
  • Face recognition
  • Training data
  • Robustness
  • Labeling
  • Convolutional neural networks

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Cam-softmax for discriminative deep feature learning'. Together they form a unique fingerprint.

Cite this