# CLAD: A Contrastive Learning based Approach for Background Debiasing

arXiv: https://arxiv.org/abs/2210.02748 · HTML: https://mlsanity.com/paper/2210.02748/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 6 Oct 2022.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [What to Hide from Your Students: Attention-Guided Masked Image Modeling](https://mlsanity.com/paper/2203.12719/) (2022)
- [Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation](https://mlsanity.com/paper/2205.14141/) (2022)
- [Social NCE: Contrastive Learning of Socially-aware Motion Representations](https://mlsanity.com/paper/2012.11717/) (2020)
- [Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs](https://mlsanity.com/paper/2110.02797/) (2021)
- [A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes](https://mlsanity.com/paper/2201.10766/) (2022)
- [Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately](https://mlsanity.com/paper/2012.04104/) (2020)
- [Shape or Texture: Understanding Discriminative Features in CNNs](https://mlsanity.com/paper/2101.11604/) (2021)
- [Object Recognition with and without Objects](https://mlsanity.com/paper/1611.06596/) (2016)
- [Object-aware Contrastive Learning for Debiased Scene Representation](https://mlsanity.com/paper/2108.00049/) (2021)
- [Comparing deep neural networks against humans: object recognition when the signal gets weaker](https://mlsanity.com/paper/1706.06969/) (2017)
- [Hold me tight! Influence of discriminative features on deep network boundaries](https://mlsanity.com/paper/2002.06349/) (2020)

## Built on by (most cited first, 6 of 6)

- [Separating common from salient patterns with Contrastive Representation Learning](https://mlsanity.com/paper/2402.11928/) (2024)
- [Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation](https://mlsanity.com/paper/2507.12292/) (2025)
- [Robust Context-Aware Object Recognition](https://mlsanity.com/paper/2510.00618/) (2025)
- [Leveraging Habitat Information for Fine-grained Bird Identification](https://mlsanity.com/paper/2312.14999/) (2023)
- [Bringing the Context Back into Object Recognition, Robustly](https://mlsanity.com/paper/2411.15933/) (2024)
- [ContextShift: A Controlled Benchmark for Context Dependence in Object Detection](https://mlsanity.com/paper/2606.09495/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious features, such as background information to make decisions. This tendency creates different problems in terms of robustness or weak generalization performance. Through our work, we introduce a contrastive learning-based approach (CLAD) to mitigate the background bias in CNNs. CLAD encourages semantic focus on object foregrounds and penalizes learning features from irrelavant backgrounds. Our method also introduces an efficient way of sampling negative samples. We achieve state-of-the-art results on the Background Challenge dataset, outperforming the previous benchmark with a margin of 4.1%. Our paper shows how CLAD serves as a proof of concept for debiasing of spurious features, such as background and texture (in supplementary material).