# Masking Strategies for Background Bias Removal in Computer Vision Models

arXiv: https://arxiv.org/abs/2308.12127 · HTML: https://mlsanity.com/paper/2308.12127/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 23 Aug 2023.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias](https://mlsanity.com/paper/2001.03152/) (2020)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Convolutional Feature Masking for Joint Object and Stuff Segmentation](https://mlsanity.com/paper/1412.1283/) (2014)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Object Recognition with and without Objects](https://mlsanity.com/paper/1611.06596/) (2016)
- [Rethinking Generalization in Few-Shot Classification](https://mlsanity.com/paper/2206.07267/) (2022)
- [Fine-grained Visual Classification with High-temperature Refinement and Background Suppression](https://mlsanity.com/paper/2303.06442/) (2023)
- [Top-Down Visual Attention from Analysis by Synthesis](https://mlsanity.com/paper/2303.13043/) (2023)

## Built on by (most cited first, 9 of 9)

- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [KARINA: An Efficient Deep Learning Model for Global Weather Forecast](https://mlsanity.com/paper/2403.10555/) (2024)
- [PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers](https://mlsanity.com/paper/2407.04538/) (2024)
- [Quantifying Context Bias in Domain Adaptation for Object Detection](https://mlsanity.com/paper/2409.14679/) (2024)
- [Two-stage Vision Transformers and Hard Masking offer Robust Object Representations](https://mlsanity.com/paper/2506.08915/) (2025)
- [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)
- [Bringing the Context Back into Object Recognition, Robustly](https://mlsanity.com/paper/2411.15933/) (2024)
- [Metonymy in vision models undermines attention-based interpretability](https://mlsanity.com/paper/2605.06095/) (2026)

## Abstract (arXiv)

Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are particularly prone to picking up background-related biases and demand robust methods to handle potential examples with out-of-distribution (OOD) backgrounds. To gain deeper insights into this critical problem, our research investigates the impact of background-induced bias on fine-grained image classification, evaluating standard backbone models such as Convolutional Neural Network (CNN) and Vision Transformers (ViT). We explore two masking strategies to mitigate background-induced bias: Early masking, which removes background information at the (input) image level, and late masking, which selectively masks high-level spatial features corresponding to the background. Extensive experiments assess the behavior of CNN and ViT models under different masking strategies, with a focus on their generalization to OOD backgrounds. The obtained findings demonstrate that both proposed strategies enhance OOD performance compared to the baseline models, with early masking consistently exhibiting the best OOD performance. Notably, a ViT variant employing GAP-Pooled Patch token-based classification combined with early masking achieves the highest OOD robustness.