# Significance of Softmax-based Features in Comparison to Distance Metric Learning-based Features

arXiv: https://arxiv.org/abs/1712.10151 · HTML: https://mlsanity.com/paper/1712.10151/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2017.

## Built on by (most cited first, 8 of 8)

- [Divide and not forget: Ensemble of selectively trained experts in Continual Learning](https://mlsanity.com/paper/2401.10191/) (2024)
- [Adaptive Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2207.01723/) (2022)
- [ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection](https://mlsanity.com/paper/2109.04047/) (2021)
- [CoReFace: Sample-Guided Contrastive Regularization for Deep Face Recognition](https://mlsanity.com/paper/2304.11668/) (2023)
- [Efficient Multimodal Neural Networks for Trigger-less Voice Assistants](https://mlsanity.com/paper/2305.12063/) (2023)
- [Learning Deep Optimal Embeddings with Sinkhorn Divergences](https://mlsanity.com/paper/2209.06469/) (2022)
- [A review of Recent Techniques for Person Re-Identification](https://mlsanity.com/paper/2509.22690/) (2025)
- [A Multi-Task Deep Learning Framework for Pose-Invariant Face Recognition and Facial Landmark Localization](https://mlsanity.com/paper/2610.16849/) (2026)

## Abstract (arXiv)

The extraction of useful deep features is important for many computer vision tasks. Deep features extracted from classification networks have proved to perform well in those tasks. To obtain features of greater usefulness, end-to-end distance metric learning (DML) has been applied to train the feature extractor directly. However, in these DML studies, there were no equitable comparisons between features extracted from a DML-based network and those from a softmax-based network. In this paper, by presenting objective comparisons between these two approaches under the same network architecture, we show that the softmax-based features perform competitive, or even better, to the state-of-the-art DML features when the size of the dataset, that is, the number of training samples per class, is large. The results suggest that softmax-based features should be properly taken into account when evaluating the performance of deep features.