Image Hashing via Cross-View Code Alignment in the Age of Foundation Models

Ilyass Moummad, Kawtar Zaher, Hervé Goeau, Alexis JolySubmission to ICLR 2026 · Withdrawn

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Efficient large-scale retrieval requires representations that are both compact and discriminative. Foundation models provide powerful visual and multimodal embeddings, but nearest neighbor search in these high-dimensional spaces is computationally expensive. Hashing offers an efficient alternative by enabling fast Hamming distance search with binary codes, yet existing approaches often rely on complex pipelines, multi-term objectives, designs specialized for a single learning paradigm, and long training times. We introduce CroVCA (Cross-View Code Alignment), a simple and unified principle for learning binary codes that remain consistent across semantically aligned views. A single binary cross-entropy loss enforces alignment, while coding-rate maximization serves as an anti-collapse regularizer to promote balanced and diverse codes. To implement this, we design HashCoder, a lightweight MLP hashing network with a final batch normalization layer to enforce balanced codes. HashCoder can be used as a probing head on frozen embeddings or to adapt encoders efficiently via LoRA fine-tuning. Across benchmarks, CroVCA achieves state-of-the-art results in just 5 training epochs. At 16 bits, it performs particularly well—for instance, unsupervised hashing on COCO completes in under 2 minutes and supervised hashing on ImageNet100 in about 3 minutes—on a single GPU. These results highlight CroVCA's efficiency, adaptability, and broad applicability.
BibTeX
@misc{moummad2025image,
  author = {Ilyass Moummad and Kawtar Zaher and Hervé Goeau and Alexis Joly},
  title = {{Image Hashing via Cross-View Code Alignment in the Age of Foundation Models}},
  year = {2025},
  eprint = {2510.27584},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.27584},
}
Figure