Proceedings Article•
Very Deep Convolutional Networks for Large-Scale Image Recognition
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.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
Citations
More filters
27 Jun 2016
TL;DR: The authors proposed two compact bilinear representations with the same discriminative power as the full Bilinear representation but with only a few thousand dimensions, which allow back-propagation of classification errors enabling an end-to-end optimization of the visual recognition system.
Abstract: Bilinear models has been shown to achieve impressive performance on a wide range of visual tasks, such as semantic segmentation, fine grained recognition and face recognition. However, bilinear features are high dimensional, typically on the order of hundreds of thousands to a few million, which makes them impractical for subsequent analysis. We propose two compact bilinear representations with the same discriminative power as the full bilinear representation but with only a few thousand dimensions. Our compact representations allow back-propagation of classification errors enabling an end-to-end optimization of the visual recognition system. The compact bilinear representations are derived through a novel kernelized analysis of bilinear pooling which provide insights into the discriminative power of bilinear pooling, and a platform for further research in compact pooling methods. Experimentation illustrate the utility of the proposed representations for image classification and few-shot learning across several datasets.
854 citations
Proceedings Article•
19 Jun 2016TL;DR: This work proposes an alternative approach that moves the computational burden to a learning stage and trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer artistic style from a given image to any other image.
Abstract: Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example. However, their methods require a slow and memory-consuming optimization process. We propose here an alternative approach that moves the computational burden to a learning stage. Given a single example of a texture, our approach trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer artistic style from a given image to any other image. The resulting networks are remarkably light-weight and can generate textures of quality comparable to Gatys et al., but hundreds of times faster. More generally, our approach highlights the power and flexibility of generative feed-forward models trained with complex and expressive loss functions.
854 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...In formulas LC(x;y) = ∑ l∈LC Nl∑ i=1 ‖F li (x)− F li (y)‖22 , (6) where Nl is the number of maps (feature channels) in layer l of the descriptor CNN....
[...]
...In practice, (Gatys et al., 2015a;b) use as texture descriptor the combination of several Gram matrices Gl, l ∈ LT , where LT contains selected indices of convolutional layer in the descriptor CNN....
[...]
...Our loss function is derived from (Gatys et al., 2015a;b) and compares image statistics extracted from a fixed pretrained descriptor CNN (usually one of the VGG CNN (Simonyan & Zisserman, 2014; Chatfield et al., 2014) which are pre-trained for image classification on the ImageNet ILSVRC 2012 data)....
[...]
...The descriptor CNN is used to measure the mismatch between the prototype texture x0 and the generated image x. Denote by F li (x) the i-th map (feature channel) computed by the l-th convolutional layer by the descriptor CNN applied to image x....
[...]
...Qualitatively, our generator CNN and (Gatys et al., 2015a)’s results are comparable and superior to the other methods; however, the generator CNN is much more efficient (see Sect....
[...]
26 Apr 2016
TL;DR: This work presents a pipeline for learning deep feature representations from multiple domains with Convolutional Neural Networks with CNNs and proposes a Domain Guided Dropout algorithm to improve the feature learning procedure.
Abstract: Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data variations. In this work, we present a pipeline for learning deep feature representations from multiple domains with Convolutional Neural Networks (CNNs). When training a CNN with data from all the domains, some neurons learn representations shared across several domains, while some others are effective only for a specific one. Based on this important observation, we propose a Domain Guided Dropout algorithm to improve the feature learning procedure. Experiments show the effectiveness of our pipeline and the proposed algorithm. Our methods on the person re-identification problem outperform stateof-the-art methods on multiple datasets by large margins.
852 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Inspired by [16, 35], we build a CNN with three preceding 3×3 convolutional layers followed by six Inception modules and two fully connected layers....
[...]
TL;DR: The technical aspect of automated driving is surveyed, with an overview of available datasets and tools for ADS development and many state-of-the-art algorithms implemented and compared on their own platform in a real-world driving setting.
Abstract: Automated driving systems (ADSs) promise a safe, comfortable and efficient driving experience. However, fatalities involving vehicles equipped with ADSs are on the rise. The full potential of ADSs cannot be realized unless the robustness of state-of-the-art is improved further. This paper discusses unsolved problems and surveys the technical aspect of automated driving. Studies regarding present challenges, high-level system architectures, emerging methodologies and core functions including localization, mapping, perception, planning, and human machine interfaces, were thoroughly reviewed. Furthermore, many state-of-the-art algorithms were implemented and compared on our own platform in a real-world driving setting. The paper concludes with an overview of available datasets and tools for ADS development.
851 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Another widely used algorithm, even faster than YOLO, is the Single Shot Detector (SSD) [138], which uses standard DCNN architectures such as VGG [131] to achieve competitive results on public benchmarks....
[...]
TL;DR: A framework for quasi real-time damage detection on video using the trained networks is developed and the robustness of the trained Faster R-CNN is evaluated and demonstrated using 11 new 6,000 × 4,000-pixel images taken of different structures.
Abstract: Computer vision-based techniques were developed to overcome the limitations of visual inspection by trained human resources and to detect structural damage in images remotely, but most methods detect only specific types of damage, such as concrete or steel cracks. To provide quasi real-time simultaneous detection of multiple types of damages, a Faster Region-based Convolutional Neural Network (Faster R-CNN)-based structural visual inspection method is proposed. To realize this, a database including 2,366 images (with 500 × 375 pixels) labeled for five types of damages—concrete crack, steel corrosion with two levels (medium and high), bolt corrosion, and steel delamination—is developed. Then, the architecture of the Faster R-CNN is modified, trained, validated, and tested using this database. Results show 90.6%, 83.4%, 82.1%, 98.1%, and 84.7% average precision (AP) ratings for the five damage types, respectively, with a mean AP of 87.8%. The robustness of the trained Faster R-CNN is evaluated and demonstrated using 11 new 6,000 × 4,000-pixel images taken of different structures. Its performance is also compared to that of the traditional CNN-based method. Considering that the proposed method provides a remarkably fast test speed (0.03 seconds per image with 500 × 375 resolution), a framework for quasi real-time damage detection on video using the trained networks is developed.
849 citations
Cites background from "Very Deep Convolutional Networks fo..."
...There are many well-known architectures for CNNs (i.e., VGG-16 (Simonyan and Zisserman, 2014), Microsoft ResNet-152 (He et al., 2016), and GoogleNet (Szegedy et al., 2015))....
[...]
..., VGG-16 (Simonyan and Zisserman, 2014), Microsoft ResNet-152 (He et al....
[...]
References
More filters
20 Jun 2009
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.
Abstract: The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.
49,639 citations
23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Abstract: Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
21,729 citations
Posted Content•
TL;DR: It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Abstract: Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a novel architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image.
9,803 citations
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Abstract: The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
9,775 citations
TL;DR: A review of the Pascal Visual Object Classes challenge from 2008-2012 and an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.
Abstract: The Pascal Visual Object Classes (VOC) challenge consists of two components: (i) a publicly available dataset of images together with ground truth annotation and standardised evaluation software; and (ii) an annual competition and workshop. There are five challenges: classification, detection, segmentation, action classification, and person layout. In this paper we provide a review of the challenge from 2008---2012. The paper is intended for two audiences: algorithm designers, researchers who want to see what the state of the art is, as measured by performance on the VOC datasets, along with the limitations and weak points of the current generation of algorithms; and, challenge designers, who want to see what we as organisers have learnt from the process and our recommendations for the organisation of future challenges. To analyse the performance of submitted algorithms on the VOC datasets we introduce a number of novel evaluation methods: a bootstrapping method for determining whether differences in the performance of two algorithms are significant or not; a normalised average precision so that performance can be compared across classes with different proportions of positive instances; a clustering method for visualising the performance across multiple algorithms so that the hard and easy images can be identified; and the use of a joint classifier over the submitted algorithms in order to measure their complementarity and combined performance. We also analyse the community's progress through time using the methods of Hoiem et al. (Proceedings of European Conference on Computer Vision, 2012) to identify the types of occurring errors. We conclude the paper with an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.
6,061 citations