# KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing

arXiv: https://arxiv.org/abs/2412.19417 · HTML: https://mlsanity.com/paper/2412.19417/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 50 references that are in the map.
- First posted on arXiv 27 Dec 2024.

## Builds on (most cited first, 3 of 3)

- [Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models](https://mlsanity.com/paper/2305.02279/) (2023)
- [Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration](https://mlsanity.com/paper/2403.11373/) (2024)
- [Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models](https://mlsanity.com/paper/2310.01356/) (2023)

## Built on by (most cited first, 2 of 2)

- [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 has been widely used for large-scale approximate nearest neighbor search due to its storage and search efficiency. However, existing deep hashing methods predominantly rely on abundant training data, leaving the more challenging scenario of low-resource adaptation for deep hashing relatively underexplored. This setting involves adapting pre-trained models to downstream tasks with only an extremely small number of training samples available. Our preliminary benchmarks reveal that current methods suffer significant performance degradation due to the distribution shift caused by limited training samples. To address these challenges, we introduce Class-Calibration LoRA (CLoRA), a novel plug-and-play approach that dynamically constructs low-rank adaptation matrices by leveraging class-level textual knowledge embeddings. CLoRA effectively incorporates prior class knowledge as anchors, enabling parameter-efficient fine-tuning while maintaining the original data distribution. Furthermore, we propose Knowledge-Guided Discrete Optimization (KIDDO), a framework to utilize class knowledge to compensate for the scarcity of visual information and enhance the discriminability of hash codes. Extensive experiments demonstrate that our proposed method, Knowledge- Anchored Low-Resource Adaptation Hashing (KALAHash), significantly boosts retrieval performance and achieves a 4x data efficiency in low-resource scenarios.