# Hashing-Baseline: Rethinking Hashing in the Age of Pretrained Models

arXiv: https://arxiv.org/abs/2509.14427 · HTML: https://mlsanity.com/paper/2509.14427/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Data Filtering Networks](https://mlsanity.com/paper/2309.17425/) (2023)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition](https://mlsanity.com/paper/2205.03433/) (2022)
- [A Survey on Deep Hashing Methods](https://mlsanity.com/paper/2003.03369/) (2020)
- [Scaling up masked audio encoder learning for general audio classification](https://mlsanity.com/paper/2406.06992/) (2024)
- [Hashing for Similarity Search: A Survey](https://mlsanity.com/paper/1408.2927/) (2014)
- [CED: Consistent ensemble distillation for audio tagging](https://mlsanity.com/paper/2308.11957/) (2023)
- [Simplifying DINO via Coding Rate Regularization](https://mlsanity.com/paper/2502.10385/) (2025)
- [The ICME 2025 Audio Encoder Capability Challenge](https://mlsanity.com/paper/2501.15302/) (2025)

## Built on by (most cited first, 1 of 1)

- [Image Hashing via Cross-View Code Alignment in the Age of Foundation Models](https://mlsanity.com/paper/2510.27584/) (2025)

## Abstract (arXiv)

Information retrieval with compact binary embeddings, also referred to as hashing, is crucial for scalable fast search applications, yet state-of-the-art hashing methods require expensive, scenario-specific training. In this work, we introduce Hashing-Baseline, a strong training-free hashing method leveraging powerful pretrained encoders that produce rich pretrained embeddings. We revisit classical, training-free hashing techniques: principal component analysis, random orthogonal projection, and threshold binarization, to produce a strong baseline for hashing. Our approach combines these techniques with frozen embeddings from state-of-the-art vision and audio encoders to yield competitive retrieval performance without any additional learning or fine-tuning. To demonstrate the generality and effectiveness of this approach, we evaluate it on standard image retrieval benchmarks as well as a newly introduced benchmark for audio hashing.