Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination

Abstract

Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional domain of supervised learning: Can we learn a good feature representation that captures apparent similarity among instances, instead of classes, by merely asking the feature to be discriminative of individual instances? We formulate this intuition as a non-parametric classification problem at the instance-level, and use noise-contrastive estimation to tackle the computational challenges imposed by the large number of instance classes. Our experimental results demonstrate that, under unsupervised learning settings, our method surpasses the state-of-the-art on ImageNet classification by a large margin. Our method is also remarkable for consistently improving test performance with more training data and better network architectures. By fine-tuning the learne

Stats

• citations2635
• S2 citations—
• github stars0
• HF likes0
• heat score25.66
• arxiv keywu2018unsupervised

Related papers

• With A Little Help From My Friends: Nearest-neighbor Contrastive Learning Of Visual Representations (2021)18.76
• Learning Non-metric Visual Similarity For Image Retrieval (2017)11.58
• Unsupervised High-level Feature Learning By Ensemble Projection For Semi-supervised Image Classification And Image Clustering (2016)0.00
• Beyond Supervised Vs. Unsupervised: Representative Benchmarking And Analysis Of Image Representation Learning (2022)8.35
• Class Agnostic Instance-level Descriptor For Visual Instance Search (2025)0.00
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
• Revisiting Contrastive Methods For Unsupervised Learning Of Visual Representations (2021)3.91
• Unsupervised Deep Features For Remote Sensing Image Matching Via Discriminator Network (2018)8.09