# Mitigating the Bias of Centered Objects in Common Datasets

arXiv: https://arxiv.org/abs/2112.09195 · HTML: https://mlsanity.com/paper/2112.09195/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location](https://mlsanity.com/paper/2003.07064/) (2020)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)

## Built on by (most cited first, 7 of 7)

- [TrailBlazer: Trajectory Control for Diffusion-Based Video Generation](https://mlsanity.com/paper/2401.00896/) (2023)
- [Multi-Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2407.06192/) (2024)
- [Zone Evaluation: Revealing Spatial Bias in Object Detection](https://mlsanity.com/paper/2310.13215/) (2023)
- [ARC: Anchored Representation Clouds for High-Resolution INR Classification](https://mlsanity.com/paper/2503.15156/) (2025)
- [Mitigating Pretraining-Induced Attention Asymmetry in 2D+ Electron Microscopy Image Segmentation](https://mlsanity.com/paper/2505.14105/) (2025)
- [SPoT: Subpixel Placement of Tokens in Vision Transformers](https://mlsanity.com/paper/2507.01654/) (2025)
- [Spanning Tree Autoregressive Visual Generation](https://mlsanity.com/paper/2511.17089/) (2025)

## Abstract (arXiv)

Convolutional networks are considered shift invariant, but it was demonstrated that their response may vary according to the exact location of the objects. In this paper we will demonstrate that most commonly investigated datasets have a bias, where objects are over-represented at the center of the image during training. This bias and the boundary condition of these networks can have a significant effect on the performance of these architectures and their accuracy drops significantly as an object approaches the boundary. We will also demonstrate how this effect can be mitigated with data augmentation techniques.