One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective

Jiun Tian Hoe, Kam Woh Ng, Tianyu Zhang, Chee Seng Chan, Yi-Zhe Song, Tao Xiang

Keywords: hashing, deep hashing, learning to hash, image retrieval, instance level retrieval

TL;DR: We unify deep hashing under a single classification objective, in the lens of cosine similarity.

Abstract: A deep hashing model typically has two main learning objectives: to make the learned binary hash codes discriminative and to minimize a quantization error. With further constraints such as bit balance and code orthogonality, it is not uncommon for existing models to employ a large number (>4) of losses. This leads to difficulties in model training and subsequently impedes their effectiveness. In this work, we propose a novel deep hashing model with only $\textit{a single learning objective}$. Specifically, we show that maximizing the cosine similarity between the continuous codes and their corresponding $\textit{binary orthogonal codes}$ can ensure both hash code discriminativeness and quantization error minimization. Further, with this learning objective, code balancing can be achieved by simply using a Batch Normalization (BN) layer and multi-label classification is also straightforward with label smoothing. The result is a one-loss deep hashing model that removes all the hassles of tuning the weights of various losses. Importantly, extensive experiments show that our model is highly effective, outperforming the state-of-the-art multi-loss hashing models on three large-scale instance retrieval benchmarks, often by significant margins.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/kamwoh/orthohash

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/one-loss-for-all-deep-hashing-with-a-single/code)