# Object Recognition with and without Objects

arXiv: https://arxiv.org/abs/1611.06596 · HTML: https://mlsanity.com/paper/1611.06596/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2016.

## Built on by (most cited first, 30 of 39)

- [Delving into Out-of-Distribution Detection with Vision-Language Representations](https://mlsanity.com/paper/2211.13445/) (2022)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [On the Impact of Spurious Correlation for Out-of-distribution Detection](https://mlsanity.com/paper/2109.05642/) (2021)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Missingness Bias in Model Debugging](https://mlsanity.com/paper/2204.08945/) (2022)
- [3DB: A Framework for Debugging Computer Vision Models](https://mlsanity.com/paper/2106.03805/) (2021)
- [Position: Measure Dataset Diversity, Don't Just Claim It](https://mlsanity.com/paper/2407.08188/) (2024)
- [When does Bias Transfer in Transfer Learning?](https://mlsanity.com/paper/2207.02842/) (2022)
- [Investigating the Benefits of Projection Head for Representation Learning](https://mlsanity.com/paper/2403.11391/) (2024)
- [Domain Generalization via Nuclear Norm Regularization](https://mlsanity.com/paper/2303.07527/) (2023)
- [Invariant Learning via Diffusion Dreamed Distribution Shifts](https://mlsanity.com/paper/2211.10370/) (2022)
- [Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation](https://mlsanity.com/paper/2112.01021/) (2021)
- [Masking Strategies for Background Bias Removal in Computer Vision Models](https://mlsanity.com/paper/2308.12127/) (2023)
- [Shape-guided Object Inpainting](https://mlsanity.com/paper/2204.07845/) (2022)
- [Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks](https://mlsanity.com/paper/2112.07921/) (2021)
- [CLAD: A Contrastive Learning based Approach for Background Debiasing](https://mlsanity.com/paper/2210.02748/) (2022)
- [ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes](https://mlsanity.com/paper/2403.04701/) (2024)
- [Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift](https://mlsanity.com/paper/2310.04971/) (2023)
- [Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement](https://mlsanity.com/paper/2109.02580/) (2021)
- [A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective](https://mlsanity.com/paper/2411.00360/) (2024)
- [Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset](https://mlsanity.com/paper/2110.07575/) (2021)
- [Developing a Series of AI Challenges for the United States Department of the Air Force](https://mlsanity.com/paper/2207.07033/) (2022)
- [XIMAGENET-12: An Explainable AI Benchmark Dataset for Model Robustness Evaluation](https://mlsanity.com/paper/2310.08182/) (2023)
- [Improving Bias Mitigation through Bias Experts in Natural Language Understanding](https://mlsanity.com/paper/2312.03577/) (2023)
- [Hybrid Sample Synthesis-based Debiasing of Classifier in Limited Data Setting](https://mlsanity.com/paper/2312.08288/) (2023)
- [Quantifying Context Bias in Domain Adaptation for Object Detection](https://mlsanity.com/paper/2409.14679/) (2024)
- [Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation](https://mlsanity.com/paper/2507.20284/) (2025)
- [The Foes of Neural Network's Data Efficiency Among Unnecessary Input Dimensions](https://mlsanity.com/paper/2107.06409/) (2021)
- [Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition](https://mlsanity.com/paper/2411.02833/) (2024)

## Abstract (arXiv)

While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and background (context) regions of images respectively. Consider- ing human recognition in the same situations, net- works trained on the pure background without ob- jects achieves highly reasonable recognition performance that beats humans by a large margin if only given context. However, humans still outperform networks with pure object available, which indicates networks and human beings have different mechanisms in understanding an image. Furthermore, we straightforwardly combine multiple trained networks to explore different visual cues learned by different networks. Experiments show that useful visual hints can be explicitly learned separately and then combined to achieve higher performance, which verifies the advantages of the proposed framework.