# Rescuing Deep Hashing from Dead Bits Problem

arXiv: https://arxiv.org/abs/2102.00648 · HTML: https://mlsanity.com/paper/2102.00648/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 14 of 14)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [Deep Cross-Modal Hashing](https://mlsanity.com/paper/1602.02255/) (2016)
- [Simultaneous Feature Learning and Hash Coding with Deep Neural Networks](https://mlsanity.com/paper/1504.03410/) (2015)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Asymmetric Deep Supervised Hashing](https://mlsanity.com/paper/1707.08325/) (2017)
- [Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval](https://mlsanity.com/paper/1501.06272/) (2015)
- [Instance-Aware Hashing for Multi-Label Image Retrieval](https://mlsanity.com/paper/1603.03234/) (2016)
- [Fast Supervised Discrete Hashing](https://mlsanity.com/paper/1904.03556/) (2019)
- [Deep Momentum Uncertainty Hashing](https://mlsanity.com/paper/2009.08012/) (2020)

## Built on by (most cited first, 4 of 4)

- [NEUCORE: Neural Concept Reasoning for Composed Image Retrieval](https://mlsanity.com/paper/2310.01358/) (2023)
- [Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration](https://mlsanity.com/paper/2403.11373/) (2024)
- [Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.22694/) (2025)
- [The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors](https://mlsanity.com/paper/2610.16977/) (2026)

## Abstract (arXiv)

Deep hashing methods have shown great retrieval accuracy and efficiency in large-scale image retrieval. How to optimize discrete hash bits is always the focus in deep hashing methods. A common strategy in these methods is to adopt an activation function, e.g. operatornamesigmoid(·) or operatornametanh(·), and minimize a quantization loss to approximate discrete values. However, this paradigm may make more and more hash bits stuck into the wrong saturated area of the activation functions and never escaped. We call this problem "Dead Bits Problem~(DBP)". Besides, the existing quantization loss will aggravate DBP as well. In this paper, we propose a simple but effective gradient amplifier which acts before activation functions to alleviate DBP. Moreover, we devise an error-aware quantization loss to further alleviate DBP. It avoids the negative effect of quantization loss based on the similarity between two images. The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods. Experimental results on three datasets demonstrate the efficiency of the proposed gradient amplifier and the error-aware quantization loss.