Results 1 - 10
of
52
Very deep convolutional networks for large-scale image recognition
, 2014
"... ar ..."
(Show Context)
Return of the Devil in the Details: Delving Deep into Convolutional Nets
, 2014
"... The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in chal-lenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compar ..."
Abstract
-
Cited by 71 (8 self)
- Add to MetaCart
The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in chal-lenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compare with each other and with previous state-of-the-art shallow representations such as the Bag-of-Visual-Words and the Improved Fisher Vector. This paper conducts a rigorous evaluation of these new techniques, exploring different deep architectures and comparing them on a common ground, identifying and disclosing important implementation details. We identify several useful properties of CNN-based representations, including the fact that the dimensionality of the CNN output layer can be reduced significantly without having an adverse effect on performance. We also identify aspects of deep and shallow methods that can be successfully shared. In particular, we show that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost. Source code and models to reproduce the experiments in the paper is made publicly available.
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
, 2015
"... Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit. PReLU ..."
Abstract
-
Cited by 40 (0 self)
- Add to MetaCart
(Show Context)
Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit. PReLU improves model fitting with nearly zero extra computational cost and little overfitting risk. Second, we derive a robust initialization method that particularly considers the rectifier nonlinearities. This method enables us to train extremely deep rectified models directly from scratch and to investigate deeper or wider network architectures. Based on the learnable activation and advanced initialization, we achieve 4.94 % top-5 test error on the ImageNet 2012 classification dataset. This is a 26 % relative improvement over the ILSVRC 2014 winner (GoogLeNet, 6.66 % [33]). To our knowledge, our result is the first1 to surpass the reported human-level performance (5.1%, [26]) on this dataset.
Fully convolutional networks for semantic segmentation
, 2014
"... Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolu-tional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmen-tation. Our key insight is to build “fully convolutional” networks that take ..."
Abstract
-
Cited by 37 (0 self)
- Add to MetaCart
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolu-tional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmen-tation. 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 convolu-tional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [17], the VGG net [28], and GoogLeNet [29]) into fully convolu-tional networks and transfer their learned representations by fine-tuning [2] to the segmentation task. We then de-fine a novel architecture that combines semantic informa-tion 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 % rela-tive improvement to 62.2 % mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image. 1.
Hypercolumns for object segmentation and fine-grained localization. arXiv:1411.5752
, 2014
"... Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a fea-ture representation. However, the information in this layer may be too coarse spatially to allow precise localization. On the contrary, earlier layers may be precise in localiza-tion but ..."
Abstract
-
Cited by 13 (0 self)
- Add to MetaCart
(Show Context)
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a fea-ture representation. However, the information in this layer may be too coarse spatially to allow precise localization. On the contrary, earlier layers may be precise in localiza-tion but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hy-percolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation [22], where we improve state-of-the-art from 49.7 mean APr [22] to 60.0, keypoint localization, where we get a 3.3 point boost over [20], and part labeling, where we show a 6.6 point gain over a strong baseline. 1.
Pcanet: A simple deep learning baseline for image classification?” arXiv preprint arXiv:1404.3606
, 2014
"... Abstract — In this paper, we propose a very simple deep learning network for image classification that is based on very basic data processing components: 1) cascaded principal com-ponent analysis (PCA); 2) binary hashing; and 3) blockwise histograms. In the proposed architecture, the PCA is employed ..."
Abstract
-
Cited by 10 (0 self)
- Add to MetaCart
(Show Context)
Abstract — In this paper, we propose a very simple deep learning network for image classification that is based on very basic data processing components: 1) cascaded principal com-ponent analysis (PCA); 2) binary hashing; and 3) blockwise histograms. In the proposed architecture, the PCA is employed to learn multistage filter banks. This is followed by simple binary hashing and block histograms for indexing and pooling. This architecture is thus called the PCA network (PCANet) and can be extremely easily and efficiently designed and learned. For comparison and to provide a better understanding, we also introduce and study two simple variations of PCANet: 1) RandNet and 2) LDANet. They share the same topology as PCANet, but their cascaded filters are either randomly selected or learned from linear discriminant analysis. We have extensively tested these basic networks on many benchmark visual data sets
Faster R-CNN: Towards real-time object detection with region proposal networks.
- In NIPS,
, 2015
"... Abstract State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
(Show Context)
Abstract State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet
Discriminative unsupervised feature learning with convolutional neural networks
- arXiv:1406.6909
"... Current methods for training convolutional neural networks depend on large amounts of labeled samples for supervised training. In this paper we present an approach for training a convolutional neural network using only unlabeled data. We train the network to discriminate between a set of surrogate c ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
(Show Context)
Current methods for training convolutional neural networks depend on large amounts of labeled samples for supervised training. In this paper we present an approach for training a convolutional neural network using only unlabeled data. We train the network to discriminate between a set of surrogate classes. Each surrogate class is formed by applying a variety of transformations to a randomly sampled ’seed ’ image patch. We find that this simple feature learning algorithm is surprisingly successful when applied to visual object recognition. The feature representation learned by our algorithm achieves classification results matching or outperforming the current state-of-the-art for unsupervised learning on several popular datasets (STL-10, CIFAR-10, Caltech-101). 1
Deformable Part Models with CNN Features
"... Abstract. In this work we report on progress in integrating deep convo-lutional features with Deformable Part Models (DPMs). We substitute the Histogram-of-Gradient features of DPMs with Convolutional Neu-ral Network (CNN) features, obtained from the top-most, fifth, convolu-tional layer of Krizhevs ..."
Abstract
-
Cited by 5 (2 self)
- Add to MetaCart
(Show Context)
Abstract. In this work we report on progress in integrating deep convo-lutional features with Deformable Part Models (DPMs). We substitute the Histogram-of-Gradient features of DPMs with Convolutional Neu-ral Network (CNN) features, obtained from the top-most, fifth, convolu-tional layer of Krizhevsky’s network [8]. We demonstrate that we thereby obtain a substantial boost in performance (+14.5 mAP) when compared to the baseline HOG-based models. This only partially bridges the gap between DPMs and the currently top-performing R-CNN method of [4], suggesting that more radical changes to DPMs may be needed. 1
