# segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection

arXiv: https://arxiv.org/abs/1502.04275 · HTML: https://mlsanity.com/paper/1502.04275/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2015.

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

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Hierarchical Object-to-Zone Graph for Object Navigation](https://mlsanity.com/paper/2109.02066/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection](https://mlsanity.com/paper/2304.03812/) (2023)
- [CNN-based Dendrite Core Detection from Microscopic Images of Directionally Solidified Ni-base Alloys](https://mlsanity.com/paper/2305.12506/) (2023)
- [Enhancing Biologically Inspired Hierarchical Temporal Memory with Hardware-Accelerated Reflex Memory](https://mlsanity.com/paper/2504.03746/) (2025)
- [Multispectral Detection Transformer with Infrared-Centric Feature Fusion](https://mlsanity.com/paper/2505.15137/) (2025)

## Abstract (arXiv)

In this paper, we propose an approach that exploits object segmentation in order to improve the accuracy of object detection. We frame the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks, and allows the hypothesis to choose and score a segment out of a large pool of accurate object segmentation proposals. This enables the detector to incorporate additional evidence when it is available and thus results in more accurate detections. Our experiments show an improvement of 4.1% in mAP over the R-CNN baseline on PASCAL VOC 2010, and 3.4% over the current state-of-the-art, demonstrating the power of our approach.