Center-wise Local Image Mixture For Contrastive Representation Learning
arXiv:2011.02697
Abstract
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples. This paper proposes a new kind of contrastive learning method, named CLIM, which uses positives from other samples in the dataset. This is achieved by searching local similar samples of the anchor, and selecting samples that are closer to the corresponding cluster center, which we denote as center-wise local image selection. The selected samples are instantiated via an data mixture strategy, which performs as a smoothing regularization. As a result, CLIM encourages both local similarity and global aggregation in a robust way, which we find is beneficial for feature representation. Besides, we introduce \emph{multi-resolution} augmentation, which enables the representation to be scale invariant. We reach 75.5% top-1 accuracy with linear evaluation over ResNet-50, and 59.3% top-1 accuracy when fine-tuned with only 1% labels.
arXiv commentAccepted by BMVC2021
References in corpus (15)
- A Simple Framework for Contrastive Learning of Visual Representations
- mixup: Beyond Empirical Risk Minimization
- Bootstrap your own latent: A new approach to self-supervised Learning
- Improved Regularization of Convolutional Neural Networks with Cutout
- Improved Baselines with Momentum Contrastive Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- What Makes for Good Views for Contrastive Learning?
- Contrastive Multiview Coding
- Prototypical Contrastive Learning of Unsupervised Representations
- Manifold Mixup: Better Representations by Interpolating Hidden States
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- Self-supervised Co-training for Video Representation Learning
- Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
- Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations