# A MultiPath Network for Object Detection

arXiv: https://arxiv.org/abs/1604.02135 · HTML: https://mlsanity.com/paper/1604.02135/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2016.

## Built on by (most cited first, 11 of 11)

- [Enhancing Adversarial Robustness via Test-time Transformation Ensembling](https://mlsanity.com/paper/2107.14110/) (2021)
- [A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation](https://mlsanity.com/paper/2105.03186/) (2021)
- [Semi-Supervised Semantic Segmentation via Marginal Contextual Information](https://mlsanity.com/paper/2308.13900/) (2023)
- [Feature Calibration Network for Occluded Pedestrian Detection](https://mlsanity.com/paper/2212.05717/) (2022)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [A Novel Incremental Learning Driven Instance Segmentation Framework to Recognize Highly Cluttered Instances of the Contraband Items](https://mlsanity.com/paper/2201.02560/) (2022)
- [High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection](https://mlsanity.com/paper/2304.03812/) (2023)
- [Automatic Cadastral Boundary Detection of Very High Resolution Images Using Mask R-CNN](https://mlsanity.com/paper/2309.16708/) (2023)
- [CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection](https://mlsanity.com/paper/2212.05691/) (2022)
- [3D shape reconstruction of semi-transparent worms](https://mlsanity.com/paper/2304.14841/) (2023)
- [Multi-Path Transformer is Better: A Case Study on Neural Machine Translation](https://mlsanity.com/paper/2305.05948/) (2023)

## Abstract (arXiv)

The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization. The result of these modifications is that information can flow along multiple paths in our network, including through features from multiple network layers and from multiple object views. We refer to our modified classifier as a "MultiPath" network. We couple our MultiPath network with DeepMask object proposals, which are well suited for localization and small objects, and adapt our pipeline to predict segmentation masks in addition to bounding boxes. The combined system improves results over the baseline Fast R-CNN detector with Selective Search by 66% overall and by 4x on small objects. It placed second in both the COCO 2015 detection and segmentation challenges.