QCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Human Action Recognition

The paper introduces QCLR, a plug‑in module that uses dual‑level quantization to robustify contrastive learning models for skeleton‑based human action recognition. By breaking gradient flow and absorbing small perturbations, QCLR protects representations from adversarial attacks while maintaining quality through an attention‑guided multi‑faceted quantization strategy. Experiments on benchmark datasets show that adding QCLR to existing contrastive learning models significantly improves robustness to both white‑box and black‑box attacks without sacrificing classification accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• efficiency
• benchmarks
• safety