Data to 7 Oct 2026

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

arXiv 1607.07155 ↗First posted 25 Jul 2016cs.CVcited by 83

Not on the map. Why?

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.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jul 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 25; 2023: 10; 2024: 7; 2025: 3; 2026: 2.

83 papers.

Sort:

By area:

2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
2021DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentationcited by 126
2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
2022HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentationcited by 94
2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
2022Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectorscited by 69
20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
2022Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Groundingcited by 52
2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 50
2022A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmarkcited by 45
20214D-Net for Learned Multi-Modal Alignmentcited by 44

38 more

2021Deep Learning for UAV-based Object Detection and Tracking: A Surveycited by 33
2022Dense Learning based Semi-Supervised Object Detectioncited by 32
2022Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-trainingcited by 32
2022Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireingcited by 30
2021Domain-Specific Suppression for Adaptive Object Detectioncited by 26
2021Pre-training strategies and datasets for facial representation learningcited by 25
2021Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognitioncited by 24
2024SFOD: Spiking Fusion Object Detectorcited by 19
2023Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistencycited by 18
2021Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scalescited by 17
2023Cascaded Zoom-in Detector for High Resolution Aerial Imagescited by 17
2021Circle Representation for Medical Object Detectioncited by 15
2022Detection Recovery in Online Multi-Object Tracking with Sparse Graph Trackercited by 15
2021Local-to-Global Self-Attention in Vision Transformerscited by 13
2022Deep Learning Serves Traffic Safety Analysis: A Forward-looking Reviewcited by 13
2021AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenescited by 11
2021MogFace: Towards a Deeper Appreciation on Face Detectioncited by 9
2021Towards Balanced Learning for Instance Recognitioncited by 9
2022Efficient High-Resolution Deep Learning: A Surveycited by 9
2021Six-channel Image Representation for Cross-domain Object Detectioncited by 8
2021Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimationcited by 8
2022Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyondcited by 8
2023Riesz networks: scale invariant neural networks in a single forward passcited by 8
2021Few-Shot Video Object Detectioncited by 7
2021NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detectioncited by 7
2021Two Eyes Are Better Than One: Exploiting Binocular Correlation for Diabetic Retinopathy Severity Gradingcited by 7
2021Multi-layered Semantic Representation Network for Multi-label Image Classificationcited by 6
2022Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUscited by 6
2021Scale Normalized Image Pyramids with AutoFocus for Object Detectioncited by 5
2022Pooling Revisited: Your Receptive Field is Suboptimalcited by 5
2022Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detectioncited by 5
2022Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformerscited by 4
2022Feature Calibration Network for Occluded Pedestrian Detectioncited by 4
2021Target Detection and Segmentation in Circular-Scan Synthetic-Aperture-Sonar Images using Semi-Supervised Convolutional Encoder-Decoderscited by 3
2021Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detectioncited by 3
2021A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasetscited by 3
2023Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Frameworkcited by 3
2024Performance Evaluation of Semi-supervised Learning Frameworks for Multi-Class Weed Detectioncited by 3

50 most cited of 83 All 83 (JSON)