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
31 Oct 2016
TL;DR: Extensive experiments show that combining RNN and C3D together can improve video-based emotion recognition noticeably, and are presented to the EmotiW 2016 Challenge.
Abstract: In this paper, we present a video-based emotion recognition system submitted to the EmotiW 2016 Challenge. The core module of this system is a hybrid network that combines recurrent neural network (RNN) and 3D convolutional networks (C3D) in a late-fusion fashion. RNN and C3D encode appearance and motion information in different ways. Specifically, RNN takes appearance features extracted by convolutional neural network (CNN) over individual video frames as input and encodes motion later, while C3D models appearance and motion of video simultaneously. Combined with an audio module, our system achieved a recognition accuracy of 59.02% without using any additional emotion-labeled video clips in training set, compared to 53.8% of the winner of EmotiW 2015. Extensive experiments show that combining RNN and C3D together can improve video-based emotion recognition noticeably.
452 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...To select a basis for the fine-tuned models, several mainstream CNN architectures trained with ImageNet are examined, including CaffeNet [10], GoogLeNet [11], VGG [13], and Residual Network [12], which perform well for general objects recognition....
[...]
...The VGGFACE model is trained on face images only, which is originally used for a face verification task....
[...]
...Meanwhile, the model after pretraining using face database (VGG-FACE) achieves the best recognition accuracy....
[...]
...In this subsection, CNN features of video faces based on the fine-tuned VGG16-FACE model are adopted....
[...]
...For the CNN-RNN network used in the paper, the CNN features of the faces are taken from fc6 layer of VGG16-Face model fine-tuned with FER2013 face emotion database [13, 16]....
[...]
01 Jun 2018
TL;DR: Experimental results and comparison with state-of-the-art methods show that the proposed GVCNN method can achieve a significant performance gain on both the 3D shape classification and retrieval tasks.
Abstract: 3D shape recognition has attracted much attention recently. Its recent advances advocate the usage of deep features and achieve the state-of-the-art performance. However, existing deep features for 3D shape recognition are restricted to a view-to-shape setting, which learns the shape descriptor from the view-level feature directly. Despite the exciting progress on view-based 3D shape description, the intrinsic hierarchical correlation and discriminability among views have not been well exploited, which is important for 3D shape representation. To tackle this issue, in this paper, we propose a group-view convolutional neural network (GVCNN) framework for hierarchical correlation modeling towards discriminative 3D shape description. The proposed GVCNN framework is composed of a hierarchical view-group-shape architecture, i.e., from the view level, the group level and the shape level, which are organized using a grouping strategy. Concretely, we first use an expanded CNN to extract a view level descriptor. Then, a grouping module is introduced to estimate the content discrimination of each view, based on which all views can be splitted into different groups according to their discriminative level. A group level description can be further generated by pooling from view descriptors. Finally, all group level descriptors are combined into the shape level descriptor according to their discriminative weights. Experimental results and comparison with state-of-the-art methods show that our proposed GVCNN method can achieve a significant performance gain on both the 3D shape classification and retrieval tasks.
452 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Using deep learning schemes for view representation typically refers to exploiting wellestablished models, such as VGG [21], GoogLeNet [23] and ResNet [9]....
[...]
...Both results demonstrate the ef- fectiveness of the proposed GVCNN. Note that GVCNN employs the GoogLeNet as the base architecture, which differs from MVCNN that uses ImageNet pre-trained VGG-m as the base architecture....
[...]
Posted Content•
TL;DR: SegLink as mentioned in this paper decomposes text into two locally detectable elements, namely segments and links, which are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network.
Abstract: Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented box covering a part of a word or text line; A link connects two adjacent segments, indicating that they belong to the same word or text line. Both elements are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network. Final detections are produced by combining segments connected by links. Compared with previous methods, SegLink improves along the dimensions of accuracy, speed, and ease of training. It achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. It runs at over 20 FPS on 512x512 images. Moreover, without modification, SegLink is able to detect long lines of non-Latin text, such as Chinese.
451 citations
07 Jun 2015
TL;DR: In this paper, a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available is proposed, which leverages deep convolutional neural networks (CNNs) to advance event detection, where only frame level static descriptors can be extracted by the existing CNN toolkits.
Abstract: In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available. The focus of this paper is to effectively leverage deep Convolutional Neural Networks (CNNs) to advance event detection, where only frame level static descriptors can be extracted by the existing CNN toolkits. This paper makes two contributions to the inference of CNN video representation. First, while average pooling and max pooling have long been the standard approaches to aggregating frame level static features, we show that performance can be significantly improved by taking advantage of an appropriate encoding method. Second, we propose using a set of latent concept descriptors as the frame descriptor, which enriches visual information while keeping it computationally affordable. The integration of the two contributions results in a new state-of-the-art performance in event detection over the largest video datasets. Compared to improved Dense Trajectories, which has been recognized as the best video representation for event detection, our new representation improves the Mean Average Precision (mAP) from 27.6% to 36.8% for the TRECVID MEDTest 14 dataset and from 34.0% to 44.6% for the TRECVID MEDTest 13 dataset.
451 citations
20 Jul 2017
TL;DR: This work proposes a deep learning approach for user-guided image colorization, which directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network.
Abstract: We propose a deep learning approach for user-guided image colorization. The system directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network (CNN). Rather than using hand-defined rules, the network propagates user edits by fusing low-level cues along with high-level semantic information, learned from large-scale data. We train on a million images, with simulated user inputs. To guide the user towards efficient input selection, the system recommends likely colors based on the input image and current user inputs. The colorization is performed in a single feed-forward pass, enabling real-time use. Even with randomly simulated user inputs, we show that the proposed system helps novice users quickly create realistic colorizations, and offers large improvements in colorization quality with just a minute of use. In addition, we demonstrate that the framework can incorporate other user "hints" to the desired colorization, showing an application to color histogram transfer.
451 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...We also utilize design principles from (Simonyan and Zisserman 2014) and (Yu and Koltun 2016)....
[...]
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