Improving Deep Regression with Ordinal Entropy

Shihao Zhang, Linlin Yang, Michael Bi Mi, Xiaoxu Zheng, Angela Yao

Keywords: regression, classification, entropy, depth estimation, counting, age estimation

TL;DR: We observe that many regression problems are preferably formulated as classification tasks, and we provide a theoretical analysis to explain this phenomenon then we propose an ordinal entropy loss to improve the performance of regression.

Abstract: In computer vision, it is often observed that formulating regression problems as a classification task yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the cross-entropy loss, outperforms regression with a mean squared error loss in its ability to learn high-entropy feature representations. Based on the analysis, we propose an ordinal entropy loss to encourage higher-entropy feature spaces while maintaining ordinal relationships to improve the performance of regression tasks. Experiments on synthetic and real-world regression tasks demonstrate the importance and benefits of increasing entropy for regression.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2301.08915/code)