Locally Supervised Deep Hybrid Model for Scene Recognition
TLDR
Zhang et al. as discussed by the authors proposed a novel locally supervised deep hybrid model (LS-DHM) that effectively enhances and explores the convolutional features for scene recognition, which achieved state-of-the-art performance.Abstract:
Convolutional neural networks (CNNs) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully connected layer of the CNN (FC-features) exhibit rich global semantic information and are extremely effective in image classification. On the other hand, the convolutional features in the middle layers of the CNN also contain meaningful local information, but are not fully explored for image representation. In this paper, we propose a novel locally supervised deep hybrid model (LS-DHM) that effectively enhances and explores the convolutional features for scene recognition. First, we notice that the convolutional features capture local objects and fine structures of scene images, which yield important cues for discriminating ambiguous scenes, whereas these features are significantly eliminated in the highly compressed FC representation. Second, we propose a new local convolutional supervision layer to enhance the local structure of the image by directly propagating the label information to the convolutional layers. Third, we propose an efficient Fisher convolutional vector (FCV) that successfully rescues the orderless mid-level semantic information (e.g., objects and textures) of scene image. The FCV encodes the large-sized convolutional maps into a fixed-length mid-level representation, and is demonstrated to be strongly complementary to the high-level FC-features. Finally, both the FCV and FC-features are collaboratively employed in the LS-DHM representation, which achieves outstanding performance in our experiments. It obtains 83.75% and 67.56% accuracies, respectively, on the heavily benchmarked MIT Indoor67 and SUN397 data sets, advancing the state-of-the-art substantially.read more
Citations
More filters
Posted Content
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
Sheng Guo,Weilin Huang,Zhang Haozhi,Chenfan Zhuang,Dong Dengke,Matthew R. Scott,Huang Dinglong +6 more
TL;DR: In this paper, a learning curriculum is designed to measure the complexity of data using its distribution density in a feature space, and rank the complexity in an unsupervised manner, resulting in a high-performance CNN model, where the negative impact of noisy labels is reduced substantially.
Book ChapterDOI
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
Sheng Guo,Weilin Huang,Zhang Haozhi,Chenfan Zhuang,Dong Dengke,Matthew R. Scott,Huang Dinglong +6 more
TL;DR: It is shown by experiments that those images with highly noisy labels can surprisingly improve the generalization capability of model, by serving as a manner of regularization, resulting in a high-performance CNN the model, where the negative impact of noisy labels is reduced substantially.
Journal ArticleDOI
Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs
TL;DR: Wang et al. as mentioned in this paper proposed a multi-resolution CNN architecture that captures visual content and structure at multiple levels and designed two knowledge guided disambiguation techniques to deal with the problem of label ambiguity.
Journal ArticleDOI
Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
TL;DR: A hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition is proposed, which achieves an excellent performance on two standard benchmarks.
Proceedings ArticleDOI
Era of deep neural networks: A review
Poonam Sharma,Akansha Singh +1 more
TL;DR: This paper reviews all the aspects and researches done till now in this area along with their future possibilities and shows great performance in deep convolution networks and recurrent nets.
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
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
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.