# Bringing the Context Back into Object Recognition, Robustly

arXiv: https://arxiv.org/abs/2411.15933 · HTML: https://mlsanity.com/paper/2411.15933/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 71 references that are in the map.
- First posted on arXiv 24 Nov 2024.

## Builds on (most cited first, 30 of 44)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [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)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [When does dough become a bagel? Analyzing the remaining mistakes on ImageNet](https://mlsanity.com/paper/2205.04596/) (2022)
- [A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes](https://mlsanity.com/paper/2201.10766/) (2022)
- [Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation](https://mlsanity.com/paper/1812.06707/) (2018)
- [Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases](https://mlsanity.com/paper/2303.05470/) (2023)

## Abstract (arXiv)

In object recognition, both the subject of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) may play an important role. However, standard supervised learning often leads to unintended over-reliance on the BG, limiting model robustness in real-world deployment settings. The problem is mainly addressed by suppressing the BG, sacrificing context information for improved generalization. We propose "Localize to Recognize Robustly" (L2R2), a novel recognition approach which exploits the benefits of context-aware classification while maintaining robustness to distribution shifts. L2R2 leverages advances in zero-shot detection to localize the FG before recognition. It improves the performance of both standard recognition with supervised training, as well as multimodal zero-shot recognition with VLMs, while being robust to long-tail BGs and distribution shifts. The results confirm localization before recognition is possible for a wide range of datasets and they highlight the limits of object detection on others