PyTorchKR Papers

최신 논문

총 10,163편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.09716

Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation

Identifying the status of individual network units is critical for understanding the mechanism of convolutional neural networks (CNNs). However, it is still challenging to reliably give a general indication of unit status, especially for units in different network models. To this end, we propose a novel method for quantitatively clarifying the status of single unit in CNN using algebraic topological tools. Unit status is indicated via the calculation of a defined topological-based entropy, called feature entropy, which measures the degree of chaos of the global spatial pattern hidden in the unit for a category. In this way, feature entropy could provide an accurate indication of status for units in different networks with diverse situations like weight-rescaling operation. Further, we show that feature entropy decreases as the layer goes deeper and shares almost simultaneous trend with loss during training. We show that by investigating the feature entropy of units on only training data, it could give discrimination between networks with different generalization ability from the view of the effectiveness of feature representations.

arXiv:2103.09669

Large-Scale Zero-Shot Image Classification from Rich and Diverse Textual Descriptions

We study the impact of using rich and diverse textual descriptions of classes for zero-shot learning (ZSL) on ImageNet. We create a new dataset ImageNet-Wiki that matches each ImageNet class to its corresponding Wikipedia article. We show that merely employing these Wikipedia articles as class descriptions yields much higher ZSL performance than prior works. Even a simple model using this type of auxiliary data outperforms state-of-the-art models that rely on standard features of word embedding encodings of class names. These results highlight the usefulness and importance of textual descriptions for ZSL, as well as the relative importance of auxiliary data type compared to algorithmic progress. Our experimental results also show that standard zero-shot learning approaches generalize poorly across categories of classes.

arXiv:2103.09384공식 코드 · Papers with Code

Triplet-Watershed for Hyperspectral Image Classification

Hyperspectral images (HSI) consist of rich spatial and spectral information, which can potentially be used for several applications. However, noise, band correlations and high dimensionality restrict the applicability of such data. This is recently addressed using creative deep learning network architectures such as ResNet, SSRN, and A2S2K. However, the last layer, i.e the classification layer, remains unchanged and is taken to be the softmax classifier. In this article, we propose to use a watershed classifier. Watershed classifier extends the watershed operator from Mathematical Morphology for classification. In its vanilla form, the watershed classifier does not have any trainable parameters. In this article, we propose a novel approach to train deep learning networks to obtain representations suitable for the watershed classifier. The watershed classifier exploits the connectivity patterns, a characteristic of HSI datasets, for better inference. We show that exploiting such characteristics allows the Triplet-Watershed to achieve state-of-art results in supervised and semi-supervised contexts. These results are validated on Indianpines (IP), University of Pavia (UP), Kennedy Space Center (KSC) and University of Houston (UH) datasets, relying on simple convnet architecture using a quarter of parameters compared to previous state-of-the-art networks. The source code for reproducing the experiments and supplementary material (high resolution images) is available at https://github.com/ac20/TripletWatershed Code.

arXiv:2103.09273공식 코드 · Papers with Code

Learning Hyperbolic Representations of Topological Features

Learning task-specific representations of persistence diagrams is an important problem in topological data analysis and machine learning. However, current state of the art methods are restricted in terms of their expressivity as they are focused on Euclidean representations. Persistence diagrams often contain features of infinite persistence (i.e., essential features) and Euclidean spaces shrink their importance relative to non-essential features because they cannot assign infinite distance to finite points. To deal with this issue, we propose a method to learn representations of persistence diagrams on hyperbolic spaces, more specifically on the Poincare ball. By representing features of infinite persistence infinitesimally close to the boundary of the ball, their distance to non-essential features approaches infinity, thereby their relative importance is preserved. This is achieved without utilizing extremely high values for the learnable parameters, thus the representation can be fed into downstream optimization methods and trained efficiently in an end-to-end fashion. We present experimental results on graph and image classification tasks and show that the performance of our method is on par with or exceeds the performance of other state of the art methods.

arXiv:2103.08640공식 코드 · Papers with Code

UPANets: Learning from the Universal Pixel Attention Networks

Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natural language processing, it is sure that now is a time of either using a Transformer-like model or hybrid CNNs with attention. However, the former need a tremendous resource to train, and the latter is in the perfect balance in this direction. In this work, to make CNNs handle global and local information, we proposed UPANets, which equips channel-wise attention with a hybrid skip-densely-connection structure. Also, the extreme-connection structure makes UPANets robust with a smoother loss landscape. In experiments, UPANets surpassed most well-known and widely-used SOTAs with an accuracy of 96.47% in Cifar-10, 80.29% in Cifar-100, and 67.67% in Tiny Imagenet. Most importantly, these performances have high parameters efficiency and only trained in one customer-based GPU. We share implementing code of UPANets in https://github.com/hanktseng131415go/UPANets.

arXiv:2103.08933

Reweighting Augmented Samples by Minimizing the Maximal Expected Loss

Data augmentation is an effective technique to improve the generalization of deep neural networks. However, previous data augmentation methods usually treat the augmented samples equally without considering their individual impacts on the model. To address this, for the augmented samples from the same training example, we propose to assign different weights to them. We construct the maximal expected loss which is the supremum over any reweighted loss on augmented samples. Inspired by adversarial training, we minimize this maximal expected loss (MMEL) and obtain a simple and interpretable closed-form solution: more attention should be paid to augmented samples with large loss values (i.e., harder examples). Minimizing this maximal expected loss enables the model to perform well under any reweighting strategy. The proposed method can generally be applied on top of any data augmentation methods. Experiments are conducted on both natural language understanding tasks with token-level data augmentation, and image classification tasks with commonly-used image augmentation techniques like random crop and horizontal flip. Empirical results show that the proposed method improves the generalization performance of the model.

arXiv:2103.08894

Distributed Deep Learning Using Volunteer Computing-Like Paradigm

Use of Deep Learning (DL) in commercial applications such as image classification, sentiment analysis and speech recognition is increasing. When training DL models with large number of parameters and/or large datasets, cost and speed of training can become prohibitive. Distributed DL training solutions that split a training job into subtasks and execute them over multiple nodes can decrease training time. However, the cost of current solutions, built predominantly for cluster computing systems, can still be an issue. In contrast to cluster computing systems, Volunteer Computing (VC) systems can lower the cost of computing, but applications running on VC systems have to handle fault tolerance, variable network latency and heterogeneity of compute nodes, and the current solutions are not designed to do so. We design a distributed solution that can run DL training on a VC system by using a data parallel approach. We implement a novel asynchronous SGD scheme called VC-ASGD suited for VC systems. In contrast to traditional VC systems that lower cost by using untrustworthy volunteer devices, we lower cost by leveraging preemptible computing instances on commercial cloud platforms. By using preemptible instances that require applications to be fault tolerant, we lower cost by 70-90% and improve data security.

arXiv:2103.08870

Learned Gradient Compression for Distributed Deep Learning

Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several computational nodes that have access to different chunks of the data. This approach, however, entails high communication rates and latency because of the computed gradients that need to be shared among nodes at every iteration. The problem becomes more pronounced in the case that there is wireless communication between the nodes (i.e. due to the limited network bandwidth). To address this problem, various compression methods have been proposed including sparsification, quantization, and entropy encoding of the gradients. Existing methods leverage the intra-node information redundancy, that is, they compress gradients at each node independently. In contrast, we advocate that the gradients across the nodes are correlated and propose methods to leverage this inter-node redundancy to improve compression efficiency. Depending on the node communication protocol (parameter server or ring-allreduce), we propose two instances of the LGC approach that we coin Learned Gradient Compression (LGC). Our methods exploit an autoencoder (i.e. trained during the first stages of the distributed training) to capture the common information that exists in the gradients of the distributed nodes. We have tested our LGC methods on the image classification and semantic segmentation tasks using different convolutional neural networks (ResNet50, ResNet101, PSPNet) and multiple datasets (ImageNet, Cifar10, CamVid). The ResNet101 model trained for image classification on Cifar10 achieved an accuracy of 93.57%, which is lower than the baseline distributed training with uncompressed gradients only by 0.18%.

arXiv:2103.08860

Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches

The security of object detection systems has attracted increasing attention, especially when facing adversarial patch attacks. Since patch attacks change the pixels in a restricted area on objects, they are easy to implement in the physical world, especially for attacking human detection systems. The existing defenses against patch attacks are mostly applied for image classification problems and have difficulty resisting human detection attacks. Towards this critical issue, we propose an efficient and effective plug-in defense component on the YOLO detection system, which we name Ad-YOLO. The main idea is to add a patch class on the YOLO architecture, which has a negligible inference increment. Thus, Ad-YOLO is expected to directly detect both the objects of interest and adversarial patches. To the best of our knowledge, our approach is the first defense strategy against human detection attacks. We investigate Ad-YOLO's performance on the YOLOv2 baseline. To improve the ability of Ad-YOLO to detect variety patches, we first use an adversarial training process to develop a patch dataset based on the Inria dataset, which we name Inria-Patch. Then, we train Ad-YOLO by a combination of Pascal VOC, Inria, and Inria-Patch datasets. With a slight drop of $0.70\%$ mAP on VOC 2007 test set, Ad-YOLO achieves $80.31\%$ AP of persons, which highly outperforms $33.93\%$ AP for YOLOv2 when facing white-box patch attacks. Furthermore, compared with YOLOv2, the results facing a physical-world attack are also included to demonstrate Ad-YOLO's excellent generalization ability.

arXiv:2103.08741공식 코드 · Papers with Code

Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification

Band selection refers to the process of choosing the most relevant bands in a hyperspectral image. By selecting a limited number of optimal bands, we aim at speeding up model training, improving accuracy, or both. It reduces redundancy among spectral bands while trying to preserve the original information of the image. By now many efforts have been made to develop unsupervised band selection approaches, of which the majority are heuristic algorithms devised by trial and error. In this paper, we are interested in training an intelligent agent that, given a hyperspectral image, is capable of automatically learning policy to select an optimal band subset without any hand-engineered reasoning. To this end, we frame the problem of unsupervised band selection as a Markov decision process, propose an effective method to parameterize it, and finally solve the problem by deep reinforcement learning. Once the agent is trained, it learns a band-selection policy that guides the agent to sequentially select bands by fully exploiting the hyperspectral image and previously picked bands. Furthermore, we propose two different reward schemes for the environment simulation of deep reinforcement learning and compare them in experiments. This, to the best of our knowledge, is the first study that explores a deep reinforcement learning model for hyperspectral image analysis, thus opening a new door for future research and showcasing the great potential of deep reinforcement learning in remote sensing applications. Extensive experiments are carried out on four hyperspectral data sets, and experimental results demonstrate the effectiveness of the proposed method.

arXiv:2103.09108공식 코드 · Papers with Code

Is it enough to optimize CNN architectures on ImageNet?

Classification performance based on ImageNet is the de-facto standard metric for CNN development. In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains. To this end, we investigate and ultimately improve ImageNet as a basis for deriving such architectures. We conduct an extensive empirical study for which we train $500$ CNN architectures, sampled from the broad AnyNetX design space, on ImageNet as well as $8$ additional well known image classification benchmark datasets from a diverse array of application domains. We observe that the performances of the architectures are highly dataset dependent. Some datasets even exhibit a negative error correlation with ImageNet across all architectures. We show how to significantly increase these correlations by utilizing ImageNet subsets restricted to fewer classes. These contributions can have a profound impact on the way we design future CNN architectures and help alleviate the tilt we see currently in our community with respect to over-reliance on one dataset.

arXiv:2103.07976공식 코드 · Papers with Code

TransFG: A Transformer Architecture for Fine-grained Recognition

Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the backbone network to extract features of detected discriminative regions. However, this strategy inevitably complicates the pipeline and pushes the proposed regions to contain most parts of the objects thus fails to locate the really important parts. Recently, vision transformer (ViT) shows its strong performance in the traditional classification task. The self-attention mechanism of the transformer links every patch token to the classification token. In this work, we first evaluate the effectiveness of the ViT framework in the fine-grained recognition setting. Then motivated by the strength of the attention link can be intuitively considered as an indicator of the importance of tokens, we further propose a novel Part Selection Module that can be applied to most of the transformer architectures where we integrate all raw attention weights of the transformer into an attention map for guiding the network to effectively and accurately select discriminative image patches and compute their relations. A contrastive loss is applied to enlarge the distance between feature representations of confusing classes. We name the augmented transformer-based model TransFG and demonstrate the value of it by conducting experiments on five popular fine-grained benchmarks where we achieve state-of-the-art performance. Qualitative results are presented for better understanding of our model.

arXiv:2103.08497

Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise

To adopt neural networks in safety critical domains, knowing whether we can trust their predictions is crucial. Bayesian neural networks (BNNs) provide uncertainty estimates by averaging predictions with respect to the posterior weight distribution. Variational inference methods for BNNs approximate the intractable weight posterior with a tractable distribution, yet mostly rely on sampling from the variational distribution during training and inference. Recent sampling-free approaches offer an alternative, but incur a significant parameter overhead. We here propose a more efficient parameterization of the posterior approximation for sampling-free variational inference that relies on the distribution induced by multiplicative Gaussian activation noise. This allows us to combine parameter efficiency with the benefits of sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks including ImageNet.

arXiv:2103.08463

How to distribute data across tasks for meta-learning?

Meta-learning models transfer the knowledge acquired from previous tasks to quickly learn new ones. They are trained on benchmarks with a fixed number of data points per task. This number is usually arbitrary and it is unknown how it affects performance at testing. Since labelling of data is expensive, finding the optimal allocation of labels across training tasks may reduce costs. Given a fixed budget of labels, should we use a small number of highly labelled tasks, or many tasks with few labels each? Should we allocate more labels to some tasks and less to others? We show that: 1) If tasks are homogeneous, there is a uniform optimal allocation, whereby all tasks get the same amount of data; 2) At fixed budget, there is a trade-off between number of tasks and number of data points per task, with a unique solution for the optimum; 3) When trained separately, harder task should get more data, at the cost of a smaller number of tasks; 4) When training on a mixture of easy and hard tasks, more data should be allocated to easy tasks. Interestingly, Neuroscience experiments have shown that human visual skills also transfer better from easy tasks. We prove these results mathematically on mixed linear regression, and we show empirically that the same results hold for few-shot image classification on CIFAR-FS and mini-ImageNet. Our results provide guidance for allocating labels across tasks when collecting data for meta-learning.

arXiv:2103.07853공식 코드 · Papers with Code

Membership Inference Attacks on Machine Learning: A Survey

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. MIAs on ML models can directly lead to a privacy breach. For example, via identifying the fact that a clinical record that has been used to train a model associated with a certain disease, an attacker can infer that the owner of the clinical record has the disease with a high chance. In recent years, MIAs have been shown to be effective on various ML models, e.g., classification models and generative models. Meanwhile, many defense methods have been proposed to mitigate MIAs. Although MIAs on ML models form a newly emerging and rapidly growing research area, there has been no systematic survey on this topic yet. In this paper, we conduct the first comprehensive survey on membership inference attacks and defenses. We provide the taxonomies for both attacks and defenses, based on their characterizations, and discuss their pros and cons. Based on the limitations and gaps identified in this survey, we point out several promising future research directions to inspire the researchers who wish to follow this area. This survey not only serves as a reference for the research community but also provides a clear description for researchers outside this research domain. To further help the researchers, we have created an online resource repository, which we will keep updated with future relevant work. Interested readers can find the repository at https://github.com/HongshengHu/membership-inference-machine-learning-literature.

arXiv:2103.07579공식 코드 · Papers with Code

Revisiting ResNets: Improved Training and Scaling Strategies

Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He et al., 2015) and studies these three aspects in an effort to disentangle them. Perhaps surprisingly, we find that training and scaling strategies may matter more than architectural changes, and further, that the resulting ResNets match recent state-of-the-art models. We show that the best performing scaling strategy depends on the training regime and offer two new scaling strategies: (1) scale model depth in regimes where overfitting can occur (width scaling is preferable otherwise); (2) increase image resolution more slowly than previously recommended (Tan & Le, 2019). Using improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1.7x - 2.7x faster than EfficientNets on TPUs, while achieving similar accuracies on ImageNet. In a large-scale semi-supervised learning setup, ResNet-RS achieves 86.2% top-1 ImageNet accuracy, while being 4.7x faster than EfficientNet NoisyStudent. The training techniques improve transfer performance on a suite of downstream tasks (rivaling state-of-the-art self-supervised algorithms) and extend to video classification on Kinetics-400. We recommend practitioners use these simple revised ResNets as baselines for future research.

arXiv:2103.07531

Uncertainty-guided Model Generalization to Unseen Domains

We study a worst-case scenario in generalization: Out-of-domain generalization from a single source. The goal is to learn a robust model from a single source and expect it to generalize over many unknown distributions. This challenging problem has been seldom investigated while existing solutions suffer from various limitations. In this paper, we propose a new solution. The key idea is to augment the source capacity in both input and label spaces, while the augmentation is guided by uncertainty assessment. To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization. The model training and deployment are effectively organized in a Bayesian meta-learning framework. We conduct extensive comparisons and ablation study to validate our approach. The results prove our superior performance in a wide scope of tasks including image classification, semantic segmentation, text classification, and speech recognition.

arXiv:2103.08504

Distance Metric-Based Learning with Interpolated Latent Features for Location Classification in Endoscopy Image and Video

Conventional Endoscopy (CE) and Wireless Capsule Endoscopy (WCE) are known tools for diagnosing gastrointestinal (GI) tract disorders. Detecting the anatomical location of GI tract can help clinicians to determine a more appropriate treatment plan, can reduce repetitive endoscopy and is important in drug-delivery. There are few research that address detecting anatomical location of WCE and CE images using classification, mainly because of difficulty in collecting data and anotating them. In this study, we present a few-shot learning method based on distance metric learning which combines transfer-learning and manifold mixup scheme for localizing endoscopy frames and can be trained on few samples. The manifold mixup process improves few-shot learning by increasing the number of training epochs while reducing overfitting, as well as providing more accurate decision boundaries. A dataset is collected from 10 different anatomical positions of human GI tract. Two models were trained using only 78 CE and 27 WCE annotated frames to predict the location of 25700 and 1825 video frames from CE and WCE, respectively. In addition, we performed subjective evaluation using nine gastroenterologists to show the necessaity of having an AI system for localization. Various ablation studies and interpretations are performed to show the importance of each step, such effect of transfer-learning approach, and impact of manifold mixup on performance. The proposed method is also compared with various methods trained on categorical cross-entropy loss and produced better results which show that proposed method has potential to be used for endoscopy image classification.

arXiv:2103.08249

Evolving parametrized Loss for Image Classification Learning on Small Datasets

This paper proposes a meta-learning approach to evolving a parametrized loss function, which is called Meta-Loss Network (MLN), for training the image classification learning on small datasets. In our approach, the MLN is embedded in the framework of classification learning as a differentiable objective function. The MLN is evolved with the Evolutionary Strategy algorithm (ES) to an optimized loss function, such that a classifier, which optimized to minimize this loss, will achieve a good generalization effect. A classifier learns on a small training dataset to minimize MLN with Stochastic Gradient Descent (SGD), and then the MLN is evolved with the precision of the small-dataset-updated classifier on a large validation dataset. In order to evaluate our approach, the MLN is trained with a large number of small sample learning tasks sampled from FashionMNIST and tested on validation tasks sampled from FashionMNIST and CIFAR10. Experiment results demonstrate that the MLN effectively improved generalization compared to classical cross-entropy error and mean squared error.

arXiv:2103.07974

CrossoverScheduler: Overlapping Multiple Distributed Training Applications in a Crossover Manner

Distributed deep learning workloads include throughput-intensive training tasks on the GPU clusters, where the Distributed Stochastic Gradient Descent (SGD) incurs significant communication delays after backward propagation, forces workers to wait for the gradient synchronization via a centralized parameter server or directly in decentralized workers. We present CrossoverScheduler, an algorithm that enables communication cycles of a distributed training application to be filled by other applications through pipelining communication and computation. With CrossoverScheduler, the running performance of distributed training can be significantly improved without sacrificing convergence rate and network accuracy. We achieve so by introducing Crossover Synchronization which allows multiple distributed deep learning applications to time-share the same GPU alternately. The prototype of CrossoverScheduler is built and integrated with Horovod. Experiments on a variety of distributed tasks show that CrossoverScheduler achieves 20% \times speedup for image classification tasks on ImageNet dataset.