Two-Way Multi-Label Loss
Author:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7476-7485
Abstract
A natural image frequently contains multiple classification targets, accordingly providing multiple class labels rather than a single label per image. While the single-label classification is effectively addressed by applying a softmax cross-entropy loss, the multi-label task is tackled mainly in a binary cross-entropy (BCE) framework. In contrast to the softmax loss, the BCE loss involves issues regarding imbalance as multiple classes are decomposed into a bunch of binary classifications; recent works improve the BCE loss to cope with the issue by means of weighting. In this paper, we propose a multi-label loss by bridging a gap between the softmax loss and the multi-label scenario. The proposed loss function is formulated on the basis of relative comparison among classes which also enables us to further improve discriminative power of features by enhancing classification margin. The loss function is so flexible as to be applicable to a multi-label setting in two ways for discriminating classes as well as samples. In the experiments on multi-label classification, the proposed method exhibits competitive performance to the other multi-label losses, and it also provides transferrable features on single-label ImageNet training. Codes are available at https://github.com/tk1980/TwowayMultiLabelLoss.Keywords
This publication has 29 references indexed in Scilit:
- Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images2017
- Densely Connected Convolutional Networks2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- CNN-RNN: A Unified Framework for Multi-label Image Classification2016
- Describing Textures in the Wild2014
- 3D Object Representations for Fine-Grained Categorization2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Multi-Label ClassificationInternational Journal of Data Warehousing and Mining, 2007
- Dimensionality Reduction by Learning an Invariant Mapping2006