# A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

arXiv: https://arxiv.org/abs/1607.07155 · HTML: https://mlsanity.com/paper/1607.07155/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2016.

## Built on by (most cited first, 30 of 83)

- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation](https://mlsanity.com/paper/2106.06716/) (2021)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Graph Stacked Hourglass Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.16385/) (2021)
- [HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation](https://mlsanity.com/paper/2207.08518/) (2022)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding](https://mlsanity.com/paper/2203.15442/) (2022)
- [MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth](https://mlsanity.com/paper/2208.02541/) (2022)
- [A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark](https://mlsanity.com/paper/2203.00131/) (2022)
- [4D-Net for Learned Multi-Modal Alignment](https://mlsanity.com/paper/2109.01066/) (2021)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [Dense Learning based Semi-Supervised Object Detection](https://mlsanity.com/paper/2204.07300/) (2022)
- [Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2207.12661/) (2022)
- [Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing](https://mlsanity.com/paper/2207.09935/) (2022)
- [Pre-training strategies and datasets for facial representation learning](https://mlsanity.com/paper/2103.16554/) (2021)
- [Domain-Specific Suppression for Adaptive Object Detection](https://mlsanity.com/paper/2105.03570/) (2021)
- [Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition](https://mlsanity.com/paper/2107.12090/) (2021)
- [SFOD: Spiking Fusion Object Detector](https://mlsanity.com/paper/2403.15192/) (2024)
- [Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency](https://mlsanity.com/paper/2303.08686/) (2023)
- [Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales](https://mlsanity.com/paper/2106.06418/) (2021)
- [Cascaded Zoom-in Detector for High Resolution Aerial Images](https://mlsanity.com/paper/2303.08747/) (2023)
- [Circle Representation for Medical Object Detection](https://mlsanity.com/paper/2110.12093/) (2021)
- [Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker](https://mlsanity.com/paper/2205.00968/) (2022)
- [Local-to-Global Self-Attention in Vision Transformers](https://mlsanity.com/paper/2107.04735/) (2021)
- [Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review](https://mlsanity.com/paper/2203.10939/) (2022)
- [AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes](https://mlsanity.com/paper/2106.10409/) (2021)
- [MogFace: Towards a Deeper Appreciation on Face Detection](https://mlsanity.com/paper/2103.11139/) (2021)
- [Towards Balanced Learning for Instance Recognition](https://mlsanity.com/paper/2108.10175/) (2021)

## Abstract (arXiv)

A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi-scale object detection. The MS-CNN consists of a proposal sub-network and a detection sub-network. In the proposal sub-network, detection is performed at multiple output layers, so that receptive fields match objects of different scales. These complementary scale-specific detectors are combined to produce a strong multi-scale object detector. The unified network is learned end-to-end, by optimizing a multi-task loss. Feature upsampling by deconvolution is also explored, as an alternative to input upsampling, to reduce the memory and computation costs. State-of-the-art object detection performance, at up to 15 fps, is reported on datasets, such as KITTI and Caltech, containing a substantial number of small objects.