Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- pp 346-361
TLDR
This work equips the networks with another pooling strategy, “spatial pyramid pooling”, to eliminate the above requirement, and develops a new network structure, called SPP-net, which can generate a fixed-length representation regardless of image size/scale.Abstract:
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g. 224×224) input image. This requirement is “artificial” and may hurt the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with a more principled pooling strategy, “spatial pyramid pooling”, to eliminate the above requirement. The new network structure, called SPP-net, can generate a fixed-length representation regardless of image size/scale. By removing the fixed-size limitation, we can improve all CNN-based image classification methods in general. Our SPP-net achieves state-of-the-art accuracy on the datasets of ImageNet 2012, Pascal VOC 2007, and Caltech101.read more
Citations
More filters
Journal ArticleDOI
Automated segmentation of macular edema in OCT using deep neural networks.
Junjie Hu,Yuanyuan Chen,Zhang Yi +2 more
TL;DR: A novel module called stochastic ASPP (sASPP) is proposed to combat the co-adaptation of multiple atrous convolutions and achieve higher segmentation accuracy compared with the state-of-the-art method.
Proceedings ArticleDOI
Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation
TL;DR: A cascade proposal and location anticipation model for frame-level action detection in temporally untrimmed videos, which shows better localization accuracy compared with single region proposal network (RPN) and demonstrates the effectiveness on the challenging UCF101 and LIRIS-HARL datasets.
Journal ArticleDOI
An enhanced SSD with feature fusion and visual reasoning for object detection
Jiaxu Leng,Ying Liu +1 more
TL;DR: An enhanced SSD is proposed, called ESSD, that improved the performance of the conventional SSD by fusing feature maps of different output layers, instead of growing layers close to the input data.
Book ChapterDOI
ColorNet: Investigating the Importance of Color Spaces for Image Classification
Shreyank N Gowda,Chun Yuan +1 more
TL;DR: In this paper, the authors explore the importance of color spaces and show that color spaces (essentially transformations of original RGB images) can significantly affect classification accuracy, and they show that certain classes of images are better represented in particular color spaces.
Posted Content
A Robust Learning Approach to Domain Adaptive Object Detection
TL;DR: A robust object detection framework that is resilient to noise in bounding box class labels, locations and size annotations is proposed that significantly improves the state-of-the-art on multiple domain adaptation scenarios on the SIM10K, Cityscapes and KITTI datasets.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
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.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
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.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
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.
Journal ArticleDOI
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.