HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
Tao Kong,Anbang Yao,Yurong Chen,Fuchun Sun +3 more
- 27 Jun 2016
- pp 845-853
TL;DR: HyperNet as discussed by the authors is based on an elaborately designed Hyper Feature which aggregates hierarchical feature maps first and then compresses them into a uniform space, thus enabling them to construct HyperNet by sharing them both in generating proposals and detecting objects via an end to end joint training strategy.
read more
Abstract: 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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Efficient Region Proposals Generation for Object Detection
Imene Bourafa,Mokhtar Taffar,Mohamed-Nadjib Zennir +2 more
- 21 Apr 2024
TL;DR: Efficient region proposals generation for object detection based on SURF keypoints. SURF-Fast-RCNN model achieves promising accuracy and mean average precision on MS-COCO dataset with 1000 region proposals.
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
TL;DR: Experimental results on three datasets demonstrate the effectiveness of the proposed zoom-out-and-in network over other state-of-the-arts, in terms of average recall for region proposal and average precision for object detection.
Group Sampling for Scale Invariant Face Detection
Xiang Ming,Fangyun Wei,Ting Zhang,Dong Chen,Fang Wen +4 more
- 01 Jun 2019
TL;DR: A group sampling method which divides the anchors into several groups according to the scale, and ensures that the number of samples for each group is the same during training, is proposed, able to advance the state-of-the-arts in face detection.
Context augmentation for object detection
Jiaxu Leng,Ying Liu +1 more
TL;DR: A context augmentation algorithm that fully utilizes contextual information to generate high-quality region proposals and detection results and effectively improves the quality of region proposals as well as recognition results is proposed.
Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition
Ayan Kumar Bhunia,Aneeshan Sain,Amandeep Kumar,Shuvozit Ghose,Pinaki Nath Chowdhury,Yi-Zhe Song +5 more
TL;DR: This paper proposes a multi-stage decoder for text recognition that integrates visual and semantic information, refining predictions in a stage-wise manner with multi-scale attention and dense connections, outperforming state-of-the-art methods in wild scenarios.
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon,Santosh K. Divvala,Ross Girshick,Ali Farhadi +3 more
- 27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.