Unsupervised Part Learning For Visual Recognition

Abstract

Part-based image classification aims at representing categories by small sets of learned discriminative parts, upon which an image representation is built. Considered as a promising avenue a decade ago, this direction has been neglected since the advent of deep neural networks. In this context, this paper brings two contributions: first, it shows that despite the recent success of end-to-end holistic models, explicit part learning can boosts classification performance. Second, this work proceeds one step further than recent part-based models (PBM), focusing on how to learn parts without using any labeled data. Instead of learning a set of parts per class, as generally done in the PBM literature, the proposed approach both constructs a partition of a given set of images into visually similar groups, and subsequently learn a set of discriminative parts per group in a fully unsupervised fashion. This strategy opens the door to the use of PBM in new applications for which the notion of ima

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keysicre2017unsupervised

Related papers

• Beyond Part Models: Person Retrieval With Refined Part Pooling (and A Strong Convolutional Baseline) (2017)24.30
• Object Category Learning And Retrieval With Weak Supervision (2018)0.00
• Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66
• Deep Unsupervised Similarity Learning Using Partially Ordered Sets (2017)9.76
• Unsupervised Part-based Weighting Aggregation Of Deep Convolutional Features For Image Retrieval (2017)14.91
• Beyond Supervised Vs. Unsupervised: Representative Benchmarking And Analysis Of Image Representation Learning (2022)8.35
• Unsupervised High-level Feature Learning By Ensemble Projection For Semi-supervised Image Classification And Image Clustering (2016)0.00
• Body Part-based Representation Learning For Occluded Person Re-identification (2022)21.32