Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Bayesian Gated Non-Negative Contrastive Learning

About

While Contrastive Learning (CL) has revolutionized self-supervised representation learning, its latent representations remain highly entangled and opaque, limiting their interpretability in safety-critical applications. We identify that a fundamental cause of this entanglement is the reliance on deterministic similarity measures, which treat all feature dimensions equally. In compositional scenes, this creates an Optimization Conflict: common background features, such as, "blue sky", are encouraged to align in positive pairs but simultaneously repelled in negative pairs, causing gradient oscillations that hinder precise semantic disentanglement. To address this, we propose BayesNCL (Bayesian Gated Non-Negative Contrastive Learning). Unlike standard approaches, BayesNCL introduces a probabilistic gating mechanism that dynamically filters out task-irrelevant, high-frequency common features while selectively retaining discriminative semantics. By formalizing feature selection as a variational inference problem with a sparse Bernoulli prior, our method effectively resolves the optimization conflict. Empirical experimental results on Imagenet-100 demonstrate that BayesNCL achieves a remarkable 142.1% improvement in semantic consistency compared to state-of-the-art baselines, yielding highly interpretable representations without compromising downstream task performance. Code is available at https://github.com/Cui-Peng-624/BayesNCL.

Peng Cui, Jiahao Zhang, Lijie Hu• 2026

Related benchmarks

TaskDatasetResultRank
Image ClassificationImageNet-100--
163
Visual Explanation EvaluationCIFAR-10 (test)--
6
Interpretability AnalysisCIFAR-100 (test)
Consistency Score22.02
5
Interpretability AnalysisImageNet-100 (test)
Consistency Score36.14
5
Image ClassificationCIFAR-100
Top-1 Accuracy60.69
4
Image RetrievalCIFAR-10
Precision@163.59
3
Image RetrievalCIFAR-100
Precision@528.47
3
Image RetrievalImageNet-100
Precision@513.13
3
Showing 8 of 8 rows

Other info

Follow for update