# Evaluating Context for Deep Object Detectors

arXiv: https://arxiv.org/abs/2205.02887 · HTML: https://mlsanity.com/paper/2205.02887/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 29 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 26 of 26)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location](https://mlsanity.com/paper/2003.07064/) (2020)
- [Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias](https://mlsanity.com/paper/2001.03152/) (2020)
- [Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks](https://mlsanity.com/paper/1512.04143/) (2015)
- [Object detection via a multi-region & semantic segmentation-aware CNN model](https://mlsanity.com/paper/1505.01749/) (2015)
- [Bag of Freebies for Training Object Detection Neural Networks](https://mlsanity.com/paper/1902.04103/) (2019)
- [Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships](https://mlsanity.com/paper/1807.00119/) (2018)
- [Putting visual object recognition in context](https://mlsanity.com/paper/1911.07349/) (2019)
- [Small Object Detection using Context and Attention](https://mlsanity.com/paper/1912.06319/) (2019)
- [CoupleNet: Coupling Global Structure with Local Parts for Object Detection](https://mlsanity.com/paper/1708.02863/) (2017)
- [Hallucination In Object Detection -- A Study In Visual Part Verification](https://mlsanity.com/paper/2106.02523/) (2021)
- [Shift Equivariance in Object Detection](https://mlsanity.com/paper/2008.05787/) (2020)
- [Seeing What Is Not There: Learning Context to Determine Where Objects Are Missing](https://mlsanity.com/paper/1702.07971/) (2017)
- [Exploring the Bounds of the Utility of Context for Object Detection](https://mlsanity.com/paper/1711.05471/) (2017)
- [Exploring Person Context and Local Scene Context for Object Detection](https://mlsanity.com/paper/1511.08177/) (2015)
- [Object Detection with Mask-based Feature Encoding](https://mlsanity.com/paper/1802.03934/) (2018)

## Built on by (most cited first, 4 of 4)

- [Humans disagree with the IoU for measuring object detector localization error](https://mlsanity.com/paper/2207.14221/) (2022)
- [VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2305.19688/) (2023)
- [Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation](https://mlsanity.com/paper/2211.14074/) (2022)
- [VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2406.18176/) (2024)

## Abstract (arXiv)

Which object detector is suitable for your context sensitive task? Deep object detectors exploit scene context for recognition differently. In this paper, we group object detectors into 3 categories in terms of context use: no context by cropping the input (RCNN), partial context by cropping the featuremap (two-stage methods) and full context without any cropping (single-stage methods). We systematically evaluate the effect of context for each deep detector category. We create a fully controlled dataset for varying context and investigate the context for deep detectors. We also evaluate gradually removing the background context and the foreground object on MS COCO. We demonstrate that single-stage and two-stage object detectors can and will use the context by virtue of their large receptive field. Thus, choosing the best object detector may depend on the application context.