# HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

arXiv: https://arxiv.org/abs/1604.00600 · HTML: https://mlsanity.com/paper/1604.00600/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2016.

## Built on by (most cited first, 30 of 46)

- [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Multi-scale Matching Networks for Semantic Correspondence](https://mlsanity.com/paper/2108.00211/) (2021)
- [PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond](https://mlsanity.com/paper/2105.02184/) (2021)
- [Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition](https://mlsanity.com/paper/2107.12090/) (2021)
- [Scale-aware Automatic Augmentation for Object Detection](https://mlsanity.com/paper/2103.17220/) (2021)
- [SFOD: Spiking Fusion Object Detector](https://mlsanity.com/paper/2403.15192/) (2024)
- [An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection](https://mlsanity.com/paper/2204.00154/) (2022)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)
- [YOLO-FaceV2: A Scale and Occlusion Aware Face Detector](https://mlsanity.com/paper/2208.02019/) (2022)
- [AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration](https://mlsanity.com/paper/2112.01740/) (2021)
- [Unsupervised Model Tree Heritage Recovery](https://mlsanity.com/paper/2405.18432/) (2024)
- [Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection](https://mlsanity.com/paper/2210.16897/) (2022)
- [AirShot: Efficient Few-Shot Detection for Autonomous Exploration](https://mlsanity.com/paper/2404.05069/) (2024)
- [Swin-Pose: Swin Transformer Based Human Pose Estimation](https://mlsanity.com/paper/2201.07384/) (2022)
- [CenterNet++ for Object Detection](https://mlsanity.com/paper/2204.08394/) (2022)
- [Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review](https://mlsanity.com/paper/2211.05120/) (2022)
- [ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery](https://mlsanity.com/paper/2409.06259/) (2024)
- [Scale Normalized Image Pyramids with AutoFocus for Object Detection](https://mlsanity.com/paper/2102.05646/) (2021)
- [Aligning What EEG Can See: Structural Representations for Brain-Vision Matching](https://mlsanity.com/paper/2603.07077/) (2026)
- [Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers](https://mlsanity.com/paper/2210.13053/) (2022)
- [AMD: Adaptive Masked Distillation for Object Detection](https://mlsanity.com/paper/2301.13538/) (2023)
- [Target Detection and Segmentation in Circular-Scan Synthetic-Aperture-Sonar Images using Semi-Supervised Convolutional Encoder-Decoders](https://mlsanity.com/paper/2101.03603/) (2021)
- [Revisiting the Loss Weight Adjustment in Object Detection](https://mlsanity.com/paper/2103.09488/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets](https://mlsanity.com/paper/2207.01806/) (2022)
- [The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition](https://mlsanity.com/paper/2409.12394/) (2024)
- [Face Attributes as Cues for Deep Face Recognition Understanding](https://mlsanity.com/paper/2105.07054/) (2021)
- [Interflow: Aggregating Multi-layer Feature Mappings with Attention Mechanism](https://mlsanity.com/paper/2106.14073/) (2021)

## Abstract (arXiv)

Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances. State-of-the-art region proposal methods usually need several thousand proposals to get high recall, thus hurting the detection efficiency. Although the latest Region Proposal Network method gets promising detection accuracy with several hundred proposals, it still struggles in small-size object detection and precise localization (e.g., large IoU thresholds), mainly due to the coarseness of its feature maps. In this paper, we present a deep hierarchical network, namely HyperNet, for handling region proposal generation and object detection jointly. Our HyperNet is primarily based on an elaborately designed Hyper Feature which aggregates hierarchical feature maps first and then compresses them into a uniform space. The Hyper Features well incorporate deep but highly semantic, intermediate but really complementary, and shallow but naturally high-resolution features of the image, thus enabling us to construct HyperNet by sharing them both in generating proposals and detecting objects via an end-to-end joint training strategy. For the deep VGG16 model, our method achieves completely leading recall and state-of-the-art object detection accuracy on PASCAL VOC 2007 and 2012 using only 100 proposals per image. It runs with a speed of 5 fps (including all steps) on a GPU, thus having the potential for real-time processing.