PyTorchKR Papers

최신 논문

총 10,163편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1903.06236공식 코드 · Papers with Code

Improving Neural Architecture Search Image Classifiers via Ensemble Learning

Finding the best neural network architecture requires significant time, resources, and human expertise. These challenges are partially addressed by neural architecture search (NAS) which is able to find the best convolutional layer or cell that is then used as a building block for the network. However, once a good building block is found, manual design is still required to assemble the final architecture as a combination of multiple blocks under a predefined parameter budget constraint. A common solution is to stack these blocks into a single tower and adjust the width and depth to fill the parameter budget. However, these single tower architectures may not be optimal. Instead, in this paper we present the AdaNAS algorithm, that uses ensemble techniques to compose a neural network as an ensemble of smaller networks automatically. Additionally, we introduce a novel technique based on knowledge distillation to iteratively train the smaller networks using the previous ensemble as a teacher. Our experiments demonstrate that ensembles of networks improve accuracy upon a single neural network while keeping the same number of parameters. Our models achieve comparable results with the state-of-the-art on CIFAR-10 and sets a new state-of-the-art on CIFAR-100.

arXiv:1903.06681

Improving Strong-Scaling of CNN Training by Exploiting Finer-Grained Parallelism

Scaling CNN training is necessary to keep up with growing datasets and reduce training time. We also see an emerging need to handle datasets with very large samples, where memory requirements for training are large. Existing training frameworks use a data-parallel approach that partitions samples within a mini-batch, but limits to scaling the mini-batch size and memory consumption makes this untenable for large samples. We describe and implement new approaches to convolution, which parallelize using spatial decomposition or a combination of sample and spatial decomposition. This introduces many performance knobs for a network, so we develop a performance model for CNNs and present a method for using it to automatically determine efficient parallelization strategies. We evaluate our algorithms with microbenchmarks and image classification with ResNet-50. Our algorithms allow us to prototype a model for a mesh-tangling dataset, where sample sizes are very large. We show that our parallelization achieves excellent strong and weak scaling and enables training for previously unreachable datasets.

arXiv:1903.06586공식 코드 · Papers with Code

Selective Kernel Networks

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the ImageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input. The code and models are available at https://github.com/implus/SKNet.

arXiv:1903.05844

Learning Dependency Structures for Weak Supervision Models

Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however, estimating the dependencies among these sources is a critical challenge. We focus on a robust PCA-based algorithm for learning these dependency structures, establish improved theoretical recovery rates, and outperform existing methods on various real-world tasks. Under certain conditions, we show that the amount of unlabeled data needed can scale sublinearly or even logarithmically with the number of sources $m$, improving over previous efforts that ignore the sparsity pattern in the dependency structure and scale linearly in $m$. We provide an information-theoretic lower bound on the minimum sample complexity of the weak supervision setting. Our method outperforms weak supervision approaches that assume conditionally-independent sources by up to 4.64 F1 points and previous structure learning approaches by up to 4.41 F1 points on real-world relation extraction and image classification tasks.

arXiv:1903.05499공식 코드 · Papers with Code

DeepOBS: A Deep Learning Optimizer Benchmark Suite

Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet, perhaps surprisingly, there is no generally agreed-upon protocol for the quantitative and reproducible evaluation of optimization strategies for deep learning. We suggest routines and benchmarks for stochastic optimization, with special focus on the unique aspects of deep learning, such as stochasticity, tunability and generalization. As the primary contribution, we present DeepOBS, a Python package of deep learning optimization benchmarks. The package addresses key challenges in the quantitative assessment of stochastic optimizers, and automates most steps of benchmarking. The library includes a wide and extensible set of ready-to-use realistic optimization problems, such as training Residual Networks for image classification on ImageNet or character-level language prediction models, as well as popular classics like MNIST and CIFAR-10. The package also provides realistic baseline results for the most popular optimizers on these test problems, ensuring a fair comparison to the competition when benchmarking new optimizers, and without having to run costly experiments. It comes with output back-ends that directly produce LaTeX code for inclusion in academic publications. It supports TensorFlow and is available open source.

arXiv:1903.05285공식 코드 · Papers with Code

All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification

Shift operation is an efficient alternative over depthwise separable convolution. However, it is still bottlenecked by its implementation manner, namely memory movement. To put this direction forward, a new and novel basic component named Sparse Shift Layer (SSL) is introduced in this paper to construct efficient convolutional neural networks. In this family of architectures, the basic block is only composed by 1x1 convolutional layers with only a few shift operations applied to the intermediate feature maps. To make this idea feasible, we introduce shift operation penalty during optimization and further propose a quantization-aware shift learning method to impose the learned displacement more friendly for inference. Extensive ablation studies indicate that only a few shift operations are sufficient to provide spatial information communication. Furthermore, to maximize the role of SSL, we redesign an improved network architecture to Fully Exploit the limited capacity of neural Network (FE-Net). Equipped with SSL, this network can achieve 75.0% top-1 accuracy on ImageNet with only 563M M-Adds. It surpasses other counterparts constructed by depthwise separable convolution and the networks searched by NAS in terms of accuracy and practical speed.

논문 ID: document/6977329

Label Consistent Fisher Vectors for Supervised Feature Aggregation

In this paper, we present a simple and efficient way to add supervised information into Fisher vectors, which has become a popular image representation method for image classification and retrieval purposes in recent years. The basic idea of our approach is to improve the Fisher kernel in the training process by adding a discriminative label comparison matrix to it. The resulting new representations, which we call Label Consistent Fisher Vectors (LCFV), can be solved for both over determined and underdetermined cases. We show that LCFV has better classification performance than traditional Fisher vectors on three public datasets.

arXiv:1903.04814

Image Classification base on PCA of Multi-view Deep Representation

In the age of information explosion, image classification is the key technology of dealing with and organizing a large number of image data. Currently, the classical image classification algorithms are mostly based on RGB images or grayscale images, and fail to make good use of the depth information about objects or scenes. The depth information in the images has a strong complementary effect, which can enhance the classification accuracy significantly. In this paper, we propose an image classification technology using principal component analysis based on multi-view depth characters. In detail, firstly, the depth image of the original image is estimated; secondly, depth characters are extracted from the RGB views and the depth view separately, and then the reducing dimension operation through the PCA is implemented. Eventually, the SVM is applied to image classification. The experimental results show that the method has good performance.

arXiv:1903.04104

Spatial-Aware Non-Local Attention for Fashion Landmark Detection

Fashion landmark detection is a challenging task even using the current deep learning techniques, due to the large variation and non-rigid deformation of clothes. In order to tackle these problems, we propose Spatial-Aware Non-Local (SANL) block, an attentive module in deep neural network which can utilize spatial information while capturing global dependency. Actually, the SANL block is constructed from the non-local block in the residual manner which can learn the spatial related representation by taking a spatial attention map from Grad-CAM. We then establish our fashion landmark detection framework on feature pyramid network, equipped with four SANL blocks in the backbone. It is demonstrated by the experimental results on two large-scale fashion datasets that our proposed fashion landmark detection approach with the SANL blocks outperforms the current state-of-the-art methods considerably. Some supplementary experiments on fine-grained image classification also show the effectiveness of the proposed SANL block.

arXiv:1903.03893

A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks

Image classification is a difficult machine learning task, where Convolutional Neural Networks (CNNs) have been applied for over 20 years in order to solve the problem. In recent years, instead of the traditional way of only connecting the current layer with its next layer, shortcut connections have been proposed to connect the current layer with its forward layers apart from its next layer, which has been proved to be able to facilitate the training process of deep CNNs. However, there are various ways to build the shortcut connections, it is hard to manually design the best shortcut connections when solving a particular problem, especially given the design of the network architecture is already very challenging. In this paper, a hybrid evolutionary computation (EC) method is proposed to \textit{automatically} evolve both the architecture of deep CNNs and the shortcut connections. Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs. The proposed algorithm is evaluated on three widely used benchmark datasets of image classification and compared with 12 peer Non-EC based competitors and one EC based competitor. The experimental results demonstrate that the proposed method outperforms all of the peer competitors in terms of classification accuracy.

arXiv:1903.04197공식 코드 · Papers with Code

Structured Knowledge Distillation for Dense Prediction

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the distillation scheme for image classification and perform knowledge distillation for each pixel separately, leading to sub-optimal performance. Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem. Specifically, we study two structured distillation schemes: i) pair-wise distillation that distills the pair-wise similarities by building a static graph; and ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by experiments on three dense prediction tasks: semantic segmentation, depth estimation and object detection. Code is available at: https://git.io/StructKD

arXiv:1903.04064

Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity between the outputs of task-specific classifiers. It provides a geometrically meaningful guidance to detect target samples that are far from the support of the source and enables efficient distribution alignment in an end-to-end trainable fashion. In the experiments, we validate the effectiveness and genericness of our method on digit and sign recognition, image classification, semantic segmentation, and object detection.

arXiv:1903.03161

Deep CNN-based Multi-task Learning for Open-Set Recognition

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task learning framework. We show that this approach results in better open-set recognition accuracy. In our approach, reconstruction errors from the decoder network are utilized for open-set rejection. In addition, we model the tail of the reconstruction error distribution from the known classes using the statistical Extreme Value Theory to improve the overall performance. Experiments on multiple image classification datasets are performed and it is shown that this method can perform significantly better than many competitive open set recognition algorithms available in the literature. The code will be made available at: github.com/otkupjnoz/mlosr.

arXiv:1903.03536

Inductive Transfer for Neural Architecture Optimization

The recent advent of automated neural network architecture search led to several methods that outperform state-of-the-art human-designed architectures. However, these approaches are computationally expensive, in extreme cases consuming GPU years. We propose two novel methods which aim to expedite this optimization problem by transferring knowledge acquired from previous tasks to new ones. First, we propose a novel neural architecture selection method which employs this knowledge to identify strong and weak characteristics of neural architectures across datasets. Thus, these characteristics do not need to be rediscovered in every search, a strong weakness of current state-of-the-art searches. Second, we propose a method for learning curve extrapolation to determine if a training process can be terminated early. In contrast to existing work, we propose to learn from learning curves of architectures trained on other datasets to improve the prediction accuracy for novel datasets. On five different image classification benchmarks, we empirically demonstrate that both of our orthogonal contributions independently lead to an acceleration, without any significant loss in accuracy.

arXiv:1903.03412

Research on the pixel-based and object-oriented methods of urban feature extraction with GF-2 remote-sensing images

During the rapid urbanization construction of China, acquisition of urban geographic information and timely data updating are important and fundamental tasks for the refined management of cities. With the development of domestic remote sensing technology, the application of Gaofen-2 (GF-2) high-resolution remote sensing images can greatly improve the accuracy of information extraction. This paper introduces an approach using object-oriented classification methods for urban feature extraction based on GF-2 satellite data. A combination of spectral, spatial attributes and membership functions was employed for mapping the urban features of Qinhuai District, Nanjing. The data preprocessing is carried out by ENVI software, and the subsequent data is exported into the eCognition software for object-oriented classification and extraction of urban feature information. Finally, the obtained raster image classification results are vectorized using the ARCGIS software, and the vector graphics are stored in the library, which can be used for further analysis and modeling. Accuracy assessment was performed using ground truth data acquired by visual interpretation and from other reliable secondary data sources. Compared with the result of pixel-based supervised (neural net) classification, the developed object-oriented method can significantly improve extraction accuracy, and after manual interpretation, an overall accuracy of 95.44% can be achieved, with a Kappa coefficient of 0.9405, which objectively confirmed the superiority of the object-oriented method and the feasibility of the utilization of GF-2 satellite data.

arXiv:1903.03087

Label Embedded Dictionary Learning for Image Classification

Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification. The objective function of LC-KSVD is consisted of reconstruction error, classification error and discriminative sparse codes error with L0-norm sparse regularization term. The L0-norm, however, leads to NP-hard problem. Despite some methods such as orthogonal matching pursuit can help solve this problem to some extent, it is quite difficult to find the optimum sparse solution. To overcome this limitation, we propose a label embedded dictionary learning (LEDL) method to utilise the L1-norm as the sparse regularization term so that we can avoid the hard-to-optimize problem by solving the convex optimization problem. Alternating direction method of multipliers and blockwise coordinate descent algorithm are then exploited to optimize the corresponding objective function. Extensive experimental results on six benchmark datasets illustrate that the proposed algorithm has achieved superior performance compared to some conventional classification algorithms.

arXiv:1903.03058

Analysis Dictionary Learning: An Efficient and Discriminative Solution

Discriminative Dictionary Learning (DL) methods have been widely advocated for image classification problems. To further sharpen their discriminative capabilities, most state-of-the-art DL methods have additional constraints included in the learning stages. These various constraints, however, lead to additional computational complexity. We hence propose an efficient Discriminative Convolutional Analysis Dictionary Learning (DCADL) method, as a lower cost Discriminative DL framework, to both characterize the image structures and refine the interclass structure representations. The proposed DCADL jointly learns a convolutional analysis dictionary and a universal classifier, while greatly reducing the time complexity in both training and testing phases, and achieving a competitive accuracy, thus demonstrating great performance in many experiments with standard databases.

arXiv:1903.02939

ViTOR: Learning to Rank Webpages Based on Visual Features

The visual appearance of a webpage carries valuable information about its quality and can be used to improve the performance of learning to rank (LTR). We introduce the Visual learning TO Rank (ViTOR) model that integrates state-of-the-art visual features extraction methods by (i) transfer learning from a pre-trained image classification model, and (ii) synthetic saliency heat maps generated from webpage snapshots. Since there is currently no public dataset for the task of LTR with visual features, we also introduce and release the ViTOR dataset, containing visually rich and diverse webpages. The ViTOR dataset consists of visual snapshots, non-visual features and relevance judgments for ClueWeb12 webpages and TREC Web Track queries. We experiment with the proposed ViTOR model on the ViTOR dataset and show that it significantly improves the performance of LTR with visual features

arXiv:1903.02827

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up

Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks trained with image level labels only tend to focus on the most discriminative parts while missing other object parts, which could provide complementary information. In this paper, we approach this problem from a different perspective. We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks. Given image level labels only, we first extract rough object instances by performing weakly supervised object detection and instance segmentation using Mask R-CNN and CRF-based segmentation. Then we estimate and search for the best parts model for each object instance under the principle of preserving as much diversity as possible. In the last stage, we build a bi-directional long short-term memory (LSTM) network to fuze and encode the partial information of these complementary parts into a comprehensive feature for image classification. Experimental results indicate that the proposed method not only achieves significant improvement over our baseline models, but also outperforms state-of-the-art algorithms by a large margin (6.7%, 2.8%, 5.2% respectively) on Stanford Dogs 120, Caltech-UCSD Birds 2011-200 and Caltech 256.

arXiv:1903.02521

Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines

Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for performing a particular function. Each algorithm consists of several hyperparameters. Algorithms and hyperparameters must be optimized as a whole to produce the best performance. Typical machine learning pipelines typically consist of complex algorithms in each of the steps. Not only is the selection process combinatorial, but it is also important to interpret and understand the pipelines. We propose a method to quantify the importance of different layers in the pipeline, by computing an error contribution relative to an agnostic choice of algorithms in that layer. We demonstrate our methodology on image classification pipelines. The agnostic methodology quantifies the error contributions from the computational steps, algorithms and hyperparameters in the image classification pipeline. We show that algorithm selection and hyper-parameter optimization methods can be used to quantify the error contribution and that random search is able to quantify the contribution more accurately than Bayesian optimization. This methodology can be used by domain experts to understand machine learning and data analysis pipelines in terms of their individual components, which can help in prioritizing different components of the pipeline.