Representation Learning Via Consistent Assignment Of Views Over Random Partitions

Abstract

We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes in an end-to-end online fashion using gradient descent without additional non-differentiable modules to solve the cluster assignment problem. CARP optimizes a new pretext task based on random partitions of prototypes that regularizes the model and enforces consistency between views' assignments. Additionally, our method improves training stability and prevents collapsed solutions in joint-embedding training. Through an extensive evaluation, we demonstrate that CARP's representations are suitable for learning downstream tasks. We evaluate CARP's representations capabilities in 17 datasets across many standard protocols, including linear evaluation, few-shot classification, k-NN, k-means, image retrieval, and copy detection. We compare CARP performance to 11 existing self-supervised methods. We extensively abla

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysilva2023representation

Related papers

• GOCA: Guided Online Cluster Assignment For Self-supervised Video Representation Learning (2022)5.24
• Self-supervised Ranking For Representation Learning (2020)0.00
• Self-organizing Visual Prototypes For Non-parametric Representation Learning (2025)0.00
• Robust Cross-modal Representation Learning With Progressive Self-distillation (2022)12.33
• Beyond Supervised Vs. Unsupervised: Representative Benchmarking And Analysis Of Image Representation Learning (2022)8.35
• Mutualvpr: A Mutual Learning Framework For Resolving Supervision Inconsistencies Via Adaptive Clustering (2024)0.00
• Patent Representation Learning Via Self-supervision (2025)0.00
• Cross-paced Representation Learning With Partial Curricula For Sketch-based Image Retrieval (2018)9.41