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
01 Jun 2016
TL;DR: A novel Expectation-Maximization (EM) based method is formulated that automatically locates discriminative patches robustly by utilizing the spatial relationships of patches and applies it to the classification of glioma and non-small-cell lung carcinoma cases into subtypes.
Abstract: Convolutional Neural Networks (CNN) are state-of-theart models for many image classification tasks. However, to recognize cancer subtypes automatically, training a CNN on gigapixel resolution Whole Slide Tissue Images (WSI) is currently computationally impossible. The differentiation of cancer subtypes is based on cellular-level visual features observed on image patch scale. Therefore, we argue that in this situation, training a patch-level classifier on image patches will perform better than or similar to an image-level classifier. The challenge becomes how to intelligently combine patch-level classification results and model the fact that not all patches will be discriminative. We propose to train a decision fusion model to aggregate patch-level predictions given by patch-level CNNs, which to the best of our knowledge has not been shown before. Furthermore, we formulate a novel Expectation-Maximization (EM) based method that automatically locates discriminative patches robustly by utilizing the spatial relationships of patches. We apply our method to the classification of glioma and non-small-cell lung carcinoma cases into subtypes. The classification accuracy of our method is similar to the inter-observer agreement between pathologists. Although it is impossible to train CNNs on WSIs, we experimentally demonstrate using a comparable non-cancer dataset of smaller images that a patch-based CNN can outperform an image-based CNN.
611 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...But instead of training a CNN, we use a pretrained 16-layer CNN model [46] to extract features from patches....
[...]
...EM-Finetune-CNN-Vote/SMI: Similar to EM-CNNVote/SMI except that instead of training a CNN from scratch, we fine-tune a pretrained 16-layer CNN model [46] by training it on discriminative patches....
[...]
...EM-Finetune-CNN-LR/SVM: Similar to EM-CNNLR/SVM except that instead of training a CNN from scratch, we fine-tune a pretrained 16-layer CNN model [46] by training it on discriminative patches....
[...]
...However, it has been shown that in many applications, learning decision fusion models can significantly improve performance compared to voting [42, 45, 24, 47, 26, 46]....
[...]
...Pretrained CNN-ImageFea-SVM: We apply a pretrained 16-layer network [46] to rail surface images to extract features, and train an SVM on these features....
[...]
27 Jun 2016
TL;DR: Wang et al. as mentioned in this paper proposed a spatial context recurrent convolutional neural network (SCRC) model for object retrieval, integrating spatial configurations and global scene-level contextual information into the network.
Abstract: In this paper, we address the task of natural language object retrieval, to localize a target object within a given image based on a natural language query of the object. Natural language object retrieval differs from text-based image retrieval task as it involves spatial information about objects within the scene and global scene context. To address this issue, we propose a novel Spatial Context Recurrent ConvNet (SCRC) model as scoring function on candidate boxes for object retrieval, integrating spatial configurations and global scene-level contextual information into the network. Our model processes query text, local image descriptors, spatial configurations and global context features through a recurrent network, outputs the probability of the query text conditioned on each candidate box as a score for the box, and can transfer visual-linguistic knowledge from image captioning domain to our task. Experimental results demonstrate that our method effectively utilizes both local and global information, outperforming previous baseline methods significantly on different datasets and scenarios, and can exploit large scale vision and language datasets for knowledge transfer.
610 citations
Posted Content•
TL;DR: Although conceptually simple, this method outperforms more complex and computationally expensive approaches that leverage semantic segmentation, instance level segmentation and flat ground priors and produces state of the art results for 3D viewpoint estimation on the Pascal 3D+ dataset.
Abstract: We present a method for 3D object detection and pose estimation from a single image. In contrast to current techniques that only regress the 3D orientation of an object, our method first regresses relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box. The first network output estimates the 3D object orientation using a novel hybrid discrete-continuous loss, which significantly outperforms the L2 loss. The second output regresses the 3D object dimensions, which have relatively little variance compared to alternatives and can often be predicted for many object types. These estimates, combined with the geometric constraints on translation imposed by the 2D bounding box, enable us to recover a stable and accurate 3D object pose. We evaluate our method on the challenging KITTI object detection benchmark both on the official metric of 3D orientation estimation and also on the accuracy of the obtained 3D bounding boxes. Although conceptually simple, our method outperforms more complex and computationally expensive approaches that leverage semantic segmentation, instance level segmentation and flat ground priors and sub-category detection. Our discrete-continuous loss also produces state of the art results for 3D viewpoint estimation on the Pascal 3D+ dataset.
608 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...The pose network is initialized with VGG [15] and fine-tuned for pose estimation using ground truth annotations from Pascal 3D+....
[...]
TL;DR: A comprehensive review of recent progress in salient object detection is provided and this field is situate among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction.
Abstract: Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep understanding of achievements and issues remains lacking. We aim to provide a comprehensive review of recent progress in salient object detection and situate this field among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction. Covering 228 publications, we survey i) roots, key concepts, and tasks, ii) core techniques and main modeling trends, and iii) datasets and evaluation metrics for salient object detection. We also discuss open problems such as evaluation metrics and dataset bias in model performance, and suggest future research directions.
608 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...loss is used to optimize the model. Li et al. [130] consider joint semantic segmentation and salient object detection. Similar to the FCN work [142], the two original fully connected layers in VGGNet [180] are replaced by convolutional layers.To overcome the fuzzy object boundaries caused by the down-sampling operations of CNNs, they make use of the SLIC [8] superpixels to model the topological relatio...
[...]
...exNet 7 10 DISC [39] TNNLS 2016 9,000 MSRA10K - 7 11 LCNN [120] Neuro 2017 2,900 MSRA-B + PASCALS AlexNet 7 12 DHSNET [137] CVPR 2016 6,000 MSRA10K VGGNet 3 13 DCL [119] CVPR 2016 2,500 MSRA-B VGGNet [180] 3 14 RACDNN [110] CVPR 2016 10,565 DUT+NJU2000+RGBD VGG 3 15 SU [109] CVPR 2016 10,000 MSRA10K VGGNet 3 16 CRPSD [187] ECCV 2016 10,000 MSRA10K VGGNet 3 17 DSRCNN [188] MM 2016 10,000 MSRA10K VGGNet ...
[...]
...ures separately. They first extract a number of features for each superpixel and feed them into a subnetwork composed of a stack of convolutional layers with 1 1 kernel size. Then, the standard VGGNet [180] is used to capture high-level features. Both low- and high12 Salient Object Detection: A Survey 13 # Model Pub Year #Training Images Training Set Pre-trained Model Fully Conv 1 SuperCNN [71] IJCV 201...
[...]
...te high-level features to lower layers allowing effective fusion of multi-level features. Another choice is exploiting stronger baseline models, such as using very deep ResNets [70] instead of VGGNet [180]. 5.2 Dataset Bias Datasets have been consequential in the rapid progress in saliency detection. On the one hand, they supply large scale training data and enable comparing performance of competing al...
[...]
Posted Content•
TL;DR: In this article, the authors proposed to fine-tune CNNs for image retrieval on a large collection of unordered images in a fully automated manner, using Reconstructed 3D models obtained by the state-of-the-art retrieval and structure-from-motion methods.
Abstract: Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant in image retrieval due to their discriminative power, compactness of representation, and search efficiency. Training of CNNs, either from scratch or fine-tuning, requires a large amount of annotated data, where a high quality of annotation is often crucial. In this work, we propose to fine-tune CNNs for image retrieval on a large collection of unordered images in a fully automated manner. Reconstructed 3D models obtained by the state-of-the-art retrieval and structure-from-motion methods guide the selection of the training data. We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval. CNN descriptor whitening discriminatively learned from the same training data outperforms commonly used PCA whitening. We propose a novel trainable Generalized-Mean (GeM) pooling layer that generalizes max and average pooling and show that it boosts retrieval performance. Applying the proposed method to the VGG network achieves state-of-the-art performance on the standard benchmarks: Oxford Buildings, Paris, and Holidays datasets.
607 citations
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