PyTorchKR Papers

최신 논문

총 10,163편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2101.09892

Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization

Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross modality and crossdomain challenges. In order to alleviate these problems, we develop a generative network-based ZSL approach equipped with the proposed Cross Knowledge Learning (CKL) scheme and Taxonomy Regularization (TR). In our approach, the semantic features are taken as inputs, and the output is the synthesized visual features generated from the corresponding semantic features. CKL enables more relevant semantic features to be trained for semantic-to-visual feature embedding in ZSL, while Taxonomy Regularization (TR) significantly improves the intersections with unseen images with more generalized visual features generated from generative network. Extensive experiments on several benchmark datasets (i.e., AwA1, AwA2, CUB, NAB and aPY) show that our approach is superior to these state-of-the-art methods in terms of ZSL image classification and retrieval.

arXiv:2101.09849

Deep Learning Generalization and the Convex Hull of Training Sets

We study the generalization of deep learning models in relation to the convex hull of their training sets. A trained image classifier basically partitions its domain via decision boundaries and assigns a class to each of those partitions. The location of decision boundaries inside the convex hull of training set can be investigated in relation to the training samples. However, our analysis shows that in standard image classification datasets, all testing images are considerably outside that convex hull, in the pixel space, in the wavelet space, and in the internal representations learned by deep networks. Therefore, the performance of a trained model partially depends on how its decision boundaries are extended outside the convex hull of its training data. From this perspective which is not studied before, over-parameterization of deep learning models may be considered a necessity for shaping the extension of decision boundaries. At the same time, over-parameterization should be accompanied by a specific training regime, in order to yield a model that not only fits the training set, but also its decision boundaries extend desirably outside the convex hull. To illustrate this, we investigate the decision boundaries of a neural network, with various degrees of parameters, inside and outside the convex hull of its training set. Moreover, we use a polynomial decision boundary to study the necessity of over-parameterization and the influence of training regime in shaping its extensions outside the convex hull of training set.

arXiv:2101.09637

DenseNet for Breast Tumor Classification in Mammographic Images

Breast cancer is the most common invasive cancer in women, and the second main cause of death. Breast cancer screening is an efficient method to detect indeterminate breast lesions early. The common approaches of screening for women are tomosynthesis and mammography images. However, the traditional manual diagnosis requires an intense workload by pathologists, who are prone to diagnostic errors. Thus, the aim of this study is to build a deep convolutional neural network method for automatic detection, segmentation, and classification of breast lesions in mammography images. Based on deep learning the Mask-CNN (RoIAlign) method was developed to features selection and extraction; and the classification was carried out by DenseNet architecture. Finally, the precision and accuracy of the model is evaluated by cross validation matrix and AUC curve. To summarize, the findings of this study may provide a helpful to improve the diagnosis and efficiency in the automatic tumor localization through the medical image classification.

arXiv:2101.09606

Learning degraded image classification with restoration data fidelity

Learning-based methods especially with convolutional neural networks (CNN) are continuously showing superior performance in computer vision applications, ranging from image classification to restoration. For image classification, most existing works focus on very clean images such as images in Caltech-256 and ImageNet datasets. However, in most realistic scenarios, the acquired images may suffer from degradation. One important and interesting problem is to combine image classification and restoration tasks to improve the performance of CNN-based classification networks on degraded images. In this report, we explore the influence of degradation types and levels on four widely-used classification networks, and the use of a restoration network to eliminate the degradation's influence. We also propose a novel method leveraging a fidelity map to calibrate the image features obtained by pre-trained classification networks. We empirically demonstrate that our proposed method consistently outperforms the pre-trained networks under all degradation levels and types with additive white Gaussian noise (AWGN), and it even outperforms the re-trained networks for degraded images under low degradation levels. We also show that the proposed method is a model-agnostic approach that benefits different classification networks. Our results reveal that the proposed method is a promising solution to mitigate the effect caused by image degradation.

arXiv:2101.09492

MinConvNets: A new class of multiplication-less Neural Networks

Convolutional Neural Networks have achieved unprecedented success in image classification, recognition, or detection applications. However, their large-scale deployment in embedded devices is still limited by the huge computational requirements, i.e., millions of MAC operations per layer. In this article, MinConvNets where the multiplications in the forward propagation are approximated by minimum comparator operations are introduced. Hardware implementation of minimum operation is much simpler than multipliers. Firstly, a methodology to find approximate operations based on statistical correlation is presented. We show that it is possible to replace multipliers by minimum operations in the forward propagation under certain constraints, i.e. given similar mean and variances of the feature and the weight vectors. A modified training method which guarantees the above constraints is proposed. And it is shown that equivalent precision can be achieved during inference with MinConvNets by using transfer learning from well trained exact CNNs.

arXiv:2101.08674공식 코드 · Papers with Code

DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition

In this work we tackle the challenging problem of anime character recognition. Anime, referring to animation produced within Japan and work derived or inspired from it. For this purpose we present DAF:re (DanbooruAnimeFaces:revamped), a large-scale, crowd-sourced, long-tailed dataset with almost 500 K images spread across more than 3000 classes. Additionally, we conduct experiments on DAF:re and similar datasets using a variety of classification models, including CNN based ResNets and self-attention based Vision Transformer (ViT). Our results give new insights into the generalization and transfer learning properties of ViT models on substantially different domain datasets from those used for the upstream pre-training, including the influence of batch and image size in their training. Additionally, we share our dataset, source-code, pre-trained checkpoints and results, as Animesion, the first end-to-end framework for large-scale anime character recognition: https://github.com/arkel23/animesion

arXiv:2101.08032

Riemannian Manifold Optimization for Discriminant Subspace Learning

Linear discriminant analysis (LDA) is a widely used algorithm in machine learning to extract a low-dimensional representation of high-dimensional data, it features to find the orthogonal discriminant projection subspace by using the Fisher discriminant criterion. However, the traditional Euclidean-based methods for solving LDA are easily convergent to spurious local minima and hardly obtain an optimal solution. To address such a problem, in this paper, we propose a novel algorithm namely Riemannian-based discriminant analysis (RDA) for subspace learning. In order to obtain an explicit solution, we transform the traditional Euclidean-based methods to the Riemannian manifold space and use the trust-region method to learn the discriminant projection subspace. We compare the proposed algorithm to existing variants of LDA, as well as the unsupervised tensor decomposition methods on image classification tasks. The numerical results suggest that RDA achieves state-of-the-art performance in classification accuracy.

arXiv:2101.0122

Simplifying Object Segmentation with PixelLib Library

PixelLib [1] is a library created to allow easy implementation of object segmentation in real life applications. In this paper we discussed in detail how PixelLib makes it possible for developers to implement semantic segmentation, instance segmentation, and background editing in images and videos with great simplification.

arXiv:2101.08030

Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data

Guaranteeing the security of transactional systems is a crucial priority of all institutions that process transactions, in order to protect their businesses against cyberattacks and fraudulent attempts. Adversarial attacks are novel techniques that, other than being proven to be effective to fool image classification models, can also be applied to tabular data. Adversarial attacks aim at producing adversarial examples, in other words, slightly modified inputs that induce the Artificial Intelligence (AI) system to return incorrect outputs that are advantageous for the attacker. In this paper we illustrate a novel approach to modify and adapt state-of-the-art algorithms to imbalanced tabular data, in the context of fraud detection. Experimental results show that the proposed modifications lead to a perfect attack success rate, obtaining adversarial examples that are also less perceptible when analyzed by humans. Moreover, when applied to a real-world production system, the proposed techniques shows the possibility of posing a serious threat to the robustness of advanced AI-based fraud detection procedures.

arXiv:2101.07995

FedNS: Improving Federated Learning for collaborative image classification on mobile clients

Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is based on taking weighted average of the client models, with the weights determined largely based on dataset sizes at the clients. In this paper, we propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. FedNS filters and re-weights the clients' models at the node/kernel level, hence leading to a potentially better global model by fusing the best components of the clients. Using collaborative image classification as an example, we show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.

arXiv:2101.07945

Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations

The task of classifying mammograms is very challenging because the lesion is usually small in the high resolution image. The current state-of-the-art approaches for medical image classification rely on using the de-facto method for ConvNets - fine-tuning. However, there are fundamental differences between natural images and medical images, which based on existing evidence from the literature, limits the overall performance gain when designed with algorithmic approaches. In this paper, we propose to go beyond fine-tuning by introducing a novel framework called MorphHR, in which we highlight a new transfer learning scheme. The idea behind the proposed framework is to integrate function-preserving transformations, for any continuous non-linear activation neurons, to internally regularise the network for improving mammograms classification. The proposed solution offers two major advantages over the existing techniques. Firstly and unlike fine-tuning, the proposed approach allows for modifying not only the last few layers but also several of the first ones on a deep ConvNet. By doing this, we can design the network front to be suitable for learning domain specific features. Secondly, the proposed scheme is scalable to hardware. Therefore, one can fit high resolution images on standard GPU memory. We show that by using high resolution images, one prevents losing relevant information. We demonstrate, through numerical and visual experiments, that the proposed approach yields to a significant improvement in the classification performance over state-of-the-art techniques, and is indeed on a par with radiology experts. Moreover and for generalisation purposes, we show the effectiveness of the proposed learning scheme on another large dataset, the ChestX-ray14, surpassing current state-of-the-art techniques.

arXiv:2101.07406

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data

We propose a novel network initialization method using Perlin noise for training image classification networks with a limited amount of data. Our main idea is to initialize the network parameters by solving an artificial noise classification problem, where the aim is to classify Perlin noise samples into their noise categories. Specifically, the proposed method consists of two steps. First, it generates Perlin noise samples with category labels defined based on noise complexity. Second, it solves a classification problem, in which network parameters are optimized to classify the generated noise samples. This method produces a reasonable set of initial weights (filters) for image classification. To the best of our knowledge, this is the first work to initialize networks by solving an artificial optimization problem without using any real-world images. Our experiments show that the proposed method outperforms conventional initialization methods on four image classification datasets.

arXiv:2101.07337

Dissonance Between Human and Machine Understanding

Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional black boxes. Consequently, there has been a recent surge in interpreting decisions of such complex models in order to explain their actions to humans. Models that correspond to human interpretation of a task are more desirable in certain contexts and can help attribute liability, build trust, expose biases and in turn build better models. It is, therefore, crucial to understand how and which models conform to human understanding of tasks. In this paper, we present a large-scale crowdsourcing study that reveals and quantifies the dissonance between human and machine understanding, through the lens of an image classification task. In particular, we seek to answer the following questions: Which (well-performing) complex ML models are closer to humans in their use of features to make accurate predictions? How does task difficulty affect the feature selection capability of machines in comparison to humans? Are humans consistently better at selecting features that make image recognition more accurate? Our findings have important implications on human-machine collaboration, considering that a long term goal in the field of artificial intelligence is to make machines capable of learning and reasoning like humans.

arXiv:2101.07312공식 코드 · Papers with Code

Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents

One of the most prominent methods for explaining the behavior of Deep Reinforcement Learning (DRL) agents is the generation of saliency maps that show how much each pixel attributed to the agents' decision. However, there is no work that computationally evaluates and compares the fidelity of different saliency map approaches specifically for DRL agents. It is particularly challenging to computationally evaluate saliency maps for DRL agents since their decisions are part of an overarching policy. For instance, the output neurons of value-based DRL algorithms encode both the value of the current state as well as the value of doing each action in this state. This ambiguity should be considered when evaluating saliency maps for such agents. In this paper, we compare five popular perturbation-based approaches to create saliency maps for DRL agents trained on four different Atari 2600 games. The approaches are compared using two computational metrics: dependence on the learned parameters of the agent (sanity checks) and fidelity to the agent's reasoning (input degradation). During the sanity checks, we encounter issues with one approach and propose a solution to fix these issues. For fidelity, we identify two main factors that influence which saliency approach should be chosen in which situation.

arXiv:2101.07308

Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains

Beyond the complexity of CNNs that require training on large annotated datasets, the domain shift between design and operational data has limited the adoption of CNNs in many real-world applications. For instance, in person re-identification, videos are captured over a distributed set of cameras with non-overlapping viewpoints. The shift between the source (e.g. lab setting) and target (e.g. cameras) domains may lead to a significant decline in recognition accuracy. Additionally, state-of-the-art CNNs may not be suitable for such real-time applications given their computational requirements. Although several techniques have recently been proposed to address domain shift problems through unsupervised domain adaptation (UDA), or to accelerate/compress CNNs through knowledge distillation (KD), we seek to simultaneously adapt and compress CNNs to generalize well across multiple target domains. In this paper, we propose a progressive KD approach for unsupervised single-target DA (STDA) and multi-target DA (MTDA) of CNNs. Our method for KD-STDA adapts a CNN to a single target domain by distilling from a larger teacher CNN, trained on both target and source domain data in order to maintain its consistency with a common representation. Our proposed approach is compared against state-of-the-art methods for compression and STDA of CNNs on the Office31 and ImageClef-DA image classification datasets. It is also compared against state-of-the-art methods for MTDA on Digits, Office31, and OfficeHome. In both settings -- KD-STDA and KD-MTDA -- results indicate that our approach can achieve the highest level of accuracy across target domains, while requiring a comparable or lower CNN complexity.

arXiv:2101.06898

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

Deep neural networks (DNNs) are increasingly deployed in different applications to achieve state-of-the-art performance. However, they are often applied as a black box with limited understanding of what knowledge the model has learned from the data. In this paper, we focus on image classification and propose a method to visualize and understand the class-wise knowledge (patterns) learned by DNNs under three different settings including natural, backdoor and adversarial. Different to existing visualization methods, our method searches for a single predictive pattern in the pixel space to represent the knowledge learned by the model for each class. Based on the proposed method, we show that DNNs trained on natural (clean) data learn abstract shapes along with some texture, and backdoored models learn a suspicious pattern for the backdoored class. Interestingly, the phenomenon that DNNs can learn a single predictive pattern for each class indicates that DNNs can learn a backdoor even from clean data, and the pattern itself is a backdoor trigger. In the adversarial setting, we show that adversarially trained models tend to learn more simplified shape patterns. Our method can serve as a useful tool to better understand the knowledge learned by DNNs on different datasets under different settings.

arXiv:2101.06749

A Layer-Wise Information Reinforcement Approach to Improve Learning in Deep Belief Networks

With the advent of deep learning, the number of works proposing new methods or improving existent ones has grown exponentially in the last years. In this scenario, "very deep" models were emerging, once they were expected to extract more intrinsic and abstract features while supporting a better performance. However, such models suffer from the gradient vanishing problem, i.e., backpropagation values become too close to zero in their shallower layers, ultimately causing learning to stagnate. Such an issue was overcome in the context of convolution neural networks by creating "shortcut connections" between layers, in a so-called deep residual learning framework. Nonetheless, a very popular deep learning technique called Deep Belief Network still suffers from gradient vanishing when dealing with discriminative tasks. Therefore, this paper proposes the Residual Deep Belief Network, which considers the information reinforcement layer-by-layer to improve the feature extraction and knowledge retaining, that support better discriminative performance. Experiments conducted over three public datasets demonstrate its robustness concerning the task of binary image classification.

arXiv:2101.07172공식 코드 · Papers with Code

HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS

We propose a new convolution neural network called HarDNet-MSEG for polyp segmentation. It achieves SOTA in both accuracy and inference speed on five popular datasets. For Kvasir-SEG, HarDNet-MSEG delivers 0.904 mean Dice running at 86.7 FPS on a GeForce RTX 2080 Ti GPU. It consists of a backbone and a decoder. The backbone is a low memory traffic CNN called HarDNet68, which has been successfully applied to various CV tasks including image classification, object detection, multi-object tracking and semantic segmentation, etc. The decoder part is inspired by the Cascaded Partial Decoder, known for fast and accurate salient object detection. We have evaluated HarDNet-MSEG using those five popular datasets. The code and all experiment details are available at Github. https://github.com/james128333/HarDNet-MSEG

arXiv:2101.06116공식 코드 · Papers with Code

Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects

Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data make accurate classification challenging for traditional methods. In the last few years, Deep Learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies on the said topic. Primarily, we will encapsulate the main challenges of traditional machine learning for HSIC and then we will acquaint the superiority of DL to address these problems. This survey breakdown the state-of-the-art DL frameworks into spectral features, spatial features, and together spatial-spectral features to systematically analyze the achievements (future research directions as well) of these frameworks for HSIC. Moreover, we will consider the fact that DL requires a large number of labeled training examples whereas acquiring such a number for HSIC is challenging in terms of time and cost. Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines.

arXiv:2101.06046공식 코드 · Papers with Code

Counterfactual Generative Networks

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object shape, deep classifiers tend to exploit spurious correlations with low-level texture or the background for solving the classification task. In this work, we take a step towards more robust and interpretable classifiers that explicitly expose the task's causal structure. Building on current advances in deep generative modeling, we propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision. By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background; hence, they allow for generating counterfactual images. We demonstrate the ability of our model to generate such images on MNIST and ImageNet. Further, we show that the counterfactual images can improve out-of-distribution robustness with a marginal drop in performance on the original classification task, despite being synthetic. Lastly, our generative model can be trained efficiently on a single GPU, exploiting common pre-trained models as inductive biases.