# Addressing Feature Suppression in Unsupervised Visual Representations

arXiv: https://arxiv.org/abs/2012.09962 · HTML: https://mlsanity.com/paper/2012.09962/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression](https://mlsanity.com/paper/2305.16536/) (2023)
- [The Clever Hans Effect in Unsupervised Learning](https://mlsanity.com/paper/2408.08041/) (2024)
- [COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training](https://mlsanity.com/paper/2412.01814/) (2024)
- [Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning](https://mlsanity.com/paper/2402.17510/) (2024)
- [Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning](https://mlsanity.com/paper/2212.08378/) (2022)
- [MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors](https://mlsanity.com/paper/2303.03679/) (2023)
- [Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features](https://mlsanity.com/paper/2308.13392/) (2023)
- [DUET: 2D Structured and Approximately Equivariant Representations](https://mlsanity.com/paper/2306.16058/) (2023)
- [Contactless Oxygen Monitoring with Gated Transformer](https://mlsanity.com/paper/2212.03357/) (2022)
- [Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense](https://mlsanity.com/paper/2409.08509/) (2024)
- [SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations](https://mlsanity.com/paper/2609.39635/) (2026)
- [VGGA: Geometry-Grounded Autoencoder for Video Generation](https://mlsanity.com/paper/2610.16204/) (2026)
- [Generative Representation Learning for Scalable Latent Tokenization](https://mlsanity.com/paper/2610.20533/) (2026)

## Abstract (arXiv)

Contrastive learning is one of the fastest growing research areas in machine learning due to its ability to learn useful representations without labeled data. However, contrastive learning is susceptible to feature suppression, i.e., it may discard important information relevant to the task of interest, and learn irrelevant features. Past work has addressed this limitation via handcrafted data augmentations that eliminate irrelevant information. This approach however does not work across all datasets and tasks. Further, data augmentations fail in addressing feature suppression in multi-attribute classification when one attribute can suppress features relevant to other attributes. In this paper, we analyze the objective function of contrastive learning and formally prove that it is vulnerable to feature suppression. We then present predictive contrastive learning (PCL), a framework for learning unsupervised representations that are robust to feature suppression. The key idea is to force the learned representation to predict the input, and hence prevent it from discarding important information. Extensive experiments verify that PCL is robust to feature suppression and outperforms state-of-the-art contrastive learning methods on a variety of datasets and tasks.