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

Information retrieval with compact binary codes, 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 pre-trained encoders that produce rich 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.<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>