# A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes

arXiv: https://arxiv.org/abs/2201.10766 · HTML: https://mlsanity.com/paper/2201.10766/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 67 references that are in the map.
- First posted on arXiv 26 Jan 2022.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [Counterfactual Generative Networks](https://mlsanity.com/paper/2101.06046/) (2021)

## Built on by (most cited first, 30 of 56)

- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Perceptual Grouping in Contrastive Vision-Language Models](https://mlsanity.com/paper/2210.09996/) (2022)
- [Simple and Fast Group Robustness by Automatic Feature Reweighting](https://mlsanity.com/paper/2306.11074/) (2023)
- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [Text-To-Concept (and Back) via Cross-Model Alignment](https://mlsanity.com/paper/2305.06386/) (2023)
- [Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning](https://mlsanity.com/paper/2304.03916/) (2023)
- [Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases](https://mlsanity.com/paper/2303.05470/) (2023)
- [Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation](https://mlsanity.com/paper/2508.06426/) (2025)
- [Explicit Tradeoffs between Adversarial and Natural Distributional Robustness](https://mlsanity.com/paper/2209.07592/) (2022)
- [Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers](https://mlsanity.com/paper/2211.15231/) (2022)
- [Probing Conceptual Understanding of Large Visual-Language Models](https://mlsanity.com/paper/2304.03659/) (2023)
- [Core Risk Minimization using Salient ImageNet](https://mlsanity.com/paper/2203.15566/) (2022)
- [Understanding Visual Feature Reliance through the Lens of Complexity](https://mlsanity.com/paper/2407.06076/) (2024)
- [Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases](https://mlsanity.com/paper/2212.02648/) (2022)
- [Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency](https://mlsanity.com/paper/2403.10717/) (2024)
- [Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models](https://mlsanity.com/paper/2505.07209/) (2025)
- [Invariant Learning via Diffusion Dreamed Distribution Shifts](https://mlsanity.com/paper/2211.10370/) (2022)
- [Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning](https://mlsanity.com/paper/2405.20439/) (2024)
- [Towards Improved Input Masking for Convolutional Neural Networks](https://mlsanity.com/paper/2211.14646/) (2022)
- [Animal Identification with Independent Foreground and Background Modeling](https://mlsanity.com/paper/2408.12930/) (2024)
- [Decouple before Align: Visual Disentanglement Enhances Prompt Tuning](https://mlsanity.com/paper/2508.00395/) (2025)
- [CLAD: A Contrastive Learning based Approach for Background Debiasing](https://mlsanity.com/paper/2210.02748/) (2022)
- [RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning](https://mlsanity.com/paper/2308.14899/) (2023)
- [Concept-based Analysis of Neural Networks via Vision-Language Models](https://mlsanity.com/paper/2403.19837/) (2024)
- [Learning Interpretable Queries for Explainable Image Classification with Information Pursuit](https://mlsanity.com/paper/2312.11548/) (2023)
- [ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes](https://mlsanity.com/paper/2403.04701/) (2024)
- [The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition](https://mlsanity.com/paper/2502.21201/) (2025)
- [Improving Concept Alignment in Vision-Language Concept Bottleneck Models](https://mlsanity.com/paper/2405.01825/) (2024)
- [Mitigating Bias: Enhancing Image Classification by Improving Model Explanations](https://mlsanity.com/paper/2307.01473/) (2023)

## Abstract (arXiv)

While datasets with single-label supervision have propelled rapid advances in image classification, additional annotations are necessary in order to quantitatively assess how models make predictions. To this end, for a subset of ImageNet samples, we collect segmentation masks for the entire object and 18 informative attributes. We call this dataset RIVAL10 (RIch Visual Attributes with Localization), consisting of roughly 26k instances over 10 classes. Using RIVAL10, we evaluate the sensitivity of a broad set of models to noise corruptions in foregrounds, backgrounds and attributes. In our analysis, we consider diverse state-of-the-art architectures (ResNets, Transformers) and training procedures (CLIP, SimCLR, DeiT, Adversarial Training). We find that, somewhat surprisingly, in ResNets, adversarial training makes models more sensitive to the background compared to foreground than standard training. Similarly, contrastively-trained models also have lower relative foreground sensitivity in both transformers and ResNets. Lastly, we observe intriguing adaptive abilities of transformers to increase relative foreground sensitivity as corruption level increases. Using saliency methods, we automatically discover spurious features that drive the background sensitivity of models and assess alignment of saliency maps with foregrounds. Finally, we quantitatively study the attribution problem for neural features by comparing feature saliency with ground-truth localization of semantic attributes.