Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning

By Zhiqiang Shen, Zechun Liu, Zhuang Liu, Marios Savvides, Trevor Darrell, Eric P. Xing. 2020

122 citations recorded by the source corpus.

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods can learn meaningful information. However, such frameworks are sometimes fragile on overfitting if the augmentations used for generating two views are not strong enough, causing the over-confident issue on the training data. This drawback hinders the model from learning subtle variance and fine-grained information. To address this, in this work we aim to involve the soft distance concept on label space in the contrastive-based unsupervised learning task and let the model be aware of the soft degree of similarity between positive or negative pairs through mixing the input data space, to further work collaboratively for the input and loss spaces. Despite its conceptual simplicity, we show empirically that with the solution -- Unsupervised image mixtures (Un-Mix), we can learn subtler, more robust and generalized representations from the transformed input and corresponding new label space. Extensive experiments are conducted on CIFAR-10, CIFAR-100, STL-10, Tiny ImageNet and standard ImageNet-1K with popular unsupervised methods SimCLR, BYOL, MoCo V1&V2, SwAV, etc. Our proposed image mixture and label assignment strategy can obtain consistent improvement by 1~3% following exactly the same hyperparameters and training procedures of the base methods. Code is publicly available at https://github.com/szq0214/Un-Mix.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning (2022, methodology): “Un-Mix [32] makes use of Mixup [4] mixture for ﬂattened contrastive predictions.”
Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study (2021, result): “This rising idea is becoming more and more dominant and has been quoted by a large number of recent literatures (Arani et al., 2019; Tang et al., 2020; Mghabbar & Ratnamogan, 2020; Shen et al., 2020; Khosla et al., 2020).”
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (2021, methodology): “Also, many interesting works [27, 17, 1, 35, 32, 13, 4] have been proposed.”