PyTorchKR Papers

최신 논문

총 11,126편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2112.05404공식 코드 · Papers with Code

The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing Dataset

In this work, we present the Large Labelled Logo Dataset (L3D), a multipurpose, hand-labelled, continuously growing dataset. It is composed of around 770k of color 256x256 RGB images extracted from the European Union Intellectual Property Office (EUIPO) open registry. Each of them is associated to multiple labels that classify the figurative and textual elements that appear in the images. These annotations have been classified by the EUIPO evaluators using the Vienna classification, a hierarchical classification of figurative marks. We suggest two direct applications of this dataset, namely, logo classification and logo generation.

arXiv:2112.05322

Dynamic hardware system for cascade SVM classification of melanoma

Melanoma is the most dangerous form of skin cancer, which is responsible for the majority of skin cancer-related deaths. Early diagnosis of melanoma can significantly reduce mortality rates and treatment costs. Therefore, skin cancer specialists are using image-based diagnostic tools for detecting melanoma earlier. We aim to develop a handheld device featured with low cost and high performance to enhance early detection of melanoma at the primary healthcare. But, developing this device is very challenging due to the complicated computations required by the embedded diagnosis system. Thus, we aim to exploit the recent hardware technology in reconfigurable computing to achieve a high-performance embedded system at low cost. Support vector machine (SVM) is a common classifier that shows high accuracy for classifying melanoma within the diagnosis system and is considered as the most compute-intensive task in the system. In this paper, we propose a dynamic hardware system for implementing a cascade SVM classifier on FPGA for early melanoma detection. A multi-core architecture is proposed to implement a two-stage cascade classifier using two classifiers with accuracies of 98% and 73%. The hardware implementation results were optimized by using the dynamic partial reconfiguration technology, where very low resource utilization of 1% slices and power consumption of 1.5 W were achieved. Consequently, the implemented dynamic hardware system meets vital embedded system constraints of high performance and low cost, resource utilization, and power consumption, while achieving efficient classification with high accuracy.

arXiv:2112.05239

On multivariate randomized classification trees: $l_0$-based sparsity, VC~dimension and decomposition methods

Decision trees are widely-used classification and regression models because of their interpretability and good accuracy. Classical methods such as CART are based on greedy approaches but a growing attention has recently been devoted to optimal decision trees. We investigate the nonlinear continuous optimization formulation proposed in Blanquero et al. (EJOR, vol. 284, 2020; COR, vol. 132, 2021) for (sparse) optimal randomized classification trees. Sparsity is important not only for feature selection but also to improve interpretability. We first consider alternative methods to sparsify such trees based on concave approximations of the $l_{0}$ ``norm". Promising results are obtained on 24 datasets in comparison with $l_1$ and $l_{\infty}$ regularizations. Then, we derive bounds on the VC dimension of multivariate randomized classification trees. Finally, since training is computationally challenging for large datasets, we propose a general decomposition scheme and an efficient version of it. Experiments on larger datasets show that the proposed decomposition method is able to significantly reduce the training times without compromising the accuracy.

arXiv:2112.05148

Classification of Anuran Frog Species Using Machine Learning

Acoustic classification of frogs has gotten a lot of attention recently due to its potential applicability in ecological investigations. Numerous studies have been presented for identifying frog species, although the majority of recorded species are thought to be monotypic. The purpose of this study is to demonstrate a method for classifying various frog species using an audio recording. To be more exact, continuous frog recordings are cut into audio snippets first (10 seconds). Then, for each ten-second recording, several time-frequency representations are constructed. Following that, rather than using manually created features, Machine Learning methods are employed to classify the frog species. Data reduction techniques; Principal Component Analysis (PCA) and Independent Component Analysis (ICA) are used to extract the most important features before classification. Finally, to validate our classification accuracy, cross validation and prediction accuracy are used. Experimental results show that PCA extracted features that achieved better classification accuracy both with cross validation and prediction accuracy.

arXiv:2112.04841

On The Effect Of Coding Artifacts On Acoustic Scene Classification

Previous DCASE challenges contributed to an increase in the performance of acoustic scene classification systems. State-of-the-art classifiers demand significant processing capabilities and memory which is challenging for resource-constrained mobile or IoT edge devices. Thus, it is more likely to deploy these models on more powerful hardware and classify audio recordings previously uploaded (or streamed) from low-power edge devices. In such scenario, the edge device may apply perceptual audio coding to reduce the transmission data rate. This paper explores the effect of perceptual audio coding on the classification performance using a DCASE 2020 challenge contribution [1]. We found that classification accuracy can degrade by up to 57% compared to classifying original (uncompressed) audio. We further demonstrate how lossy audio compression techniques during model training can improve classification accuracy of compressed audio signals even for audio codecs and codec bitrates not included in the training process.

arXiv:2112.04788공식 코드 · Papers with Code

"What can I cook with these ingredients?" -- Understanding cooking-related information needs in conversational search

As conversational search becomes more pervasive, it becomes increasingly important to understand the user's underlying information needs when they converse with such systems in diverse domains. We conduct an in-situ study to understand information needs arising in a home cooking context as well as how they are verbally communicated to an assistant. A human experimenter plays this role in our study. Based on the transcriptions of utterances, we derive a detailed hierarchical taxonomy of diverse information needs occurring in this context, which require different levels of assistance to be solved. The taxonomy shows that needs can be communicated through different linguistic means and require different amounts of context to be understood. In a second contribution we perform classification experiments to determine the feasibility of predicting the type of information need a user has during a dialogue using the turn provided. For this multi-label classification problem, we achieve average F1 measures of 40% using BERT-based models. We demonstrate with examples, which types of need are difficult to predict and show why, concluding that models need to include more context information in order to improve both information need classification and assistance to make such systems usable.

arXiv:2112.04539공식 코드 · Papers with Code

Prompt-based Zero-shot Relation Extraction with Semantic Knowledge Augmentation

In relation triplet extraction (RTE), recognizing unseen relations for which there are no training instances is a challenging task. Efforts have been made to recognize unseen relations based on question-answering models or relation descriptions. However, these approaches miss the semantic information about connections between seen and unseen relations. In this paper, We propose a prompt-based model with semantic knowledge augmentation (ZS-SKA) to recognize unseen relations under the zero-shot setting. We present a new word-level analogy-based sentence translation rule and generate augmented instances with unseen relations from instances with seen relations using that new rule. We design prompts with weighted virtual label construction based on an external knowledge graph to integrate semantic knowledge information learned from seen relations. Instead of using the actual label sets in the prompt template, we construct weighted virtual label words. We learn the representations of both seen and unseen relations with augmented instances and prompts. We then calculate the distance between the generated representations using prototypical networks to predict unseen relations. Extensive experiments conducted on three public datasets FewRel, Wiki-ZSL, and NYT, show that ZS-SKA outperforms other methods under zero-shot setting. Results also demonstrate the effectiveness and robustness of ZS-SKA.

arXiv:2112.04720

Amicable Aid: Perturbing Images to Improve Classification Performance

While adversarial perturbation of images to attack deep image classification models pose serious security concerns in practice, this paper suggests a novel paradigm where the concept of image perturbation can benefit classification performance, which we call amicable aid. We show that by taking the opposite search direction of perturbation, an image can be modified to yield higher classification confidence and even a misclassified image can be made correctly classified. This can be also achieved with a large amount of perturbation by which the image is made unrecognizable by human eyes. The mechanism of the amicable aid is explained in the viewpoint of the underlying natural image manifold. Furthermore, we investigate the universal amicable aid, i.e., a fixed perturbation can be applied to multiple images to improve their classification results. While it is challenging to find such perturbations, we show that making the decision boundary as perpendicular to the image manifold as possible via training with modified data is effective to obtain a model for which universal amicable perturbations are more easily found.

arXiv:2112.04585공식 코드 · Papers with Code

MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification

We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification. MASTAF takes input from a general video spatial and temporal representation,e.g., using 2D CNN, 3D CNN, and Video Transformer. Then, to make the most of such representations, we use self- and cross-attention models to highlight the critical spatio-temporal region to increase the inter-class variations and decrease the intra-class variations. Last, MASTAF applies a lightweight fusion network and a nearest neighbor classifier to classify each query video. We demonstrate that MASTAF improves the state-of-the-art performance on three few-shot video classification benchmarks(UCF101, HMDB51, and Something-Something-V2), e.g., by up to 91.6%, 69.5%, and 60.7% for five-way one-shot video classification, respectively.

arXiv:2112.04572

Merging Subject Matter Expertise and Deep Convolutional Neural Network for State-Based Online Machine-Part Interaction Classification

Machine-part interaction classification is a key capability required by Cyber-Physical Systems (CPS), a pivotal enabler of Smart Manufacturing (SM). While previous relevant studies on the subject have primarily focused on time series classification, change point detection is equally important because it provides temporal information on changes in behavior of the machine. In this work, we address point detection and time series classification for machine-part interactions with a deep Convolutional Neural Network (CNN) based framework. The CNN in this framework utilizes a two-stage encoder-classifier structure for efficient feature representation and convenient deployment customization for CPS. Though data-driven, the design and optimization of the framework are Subject Matter Expertise (SME) guided. An SME defined Finite State Machine (FSM) is incorporated into the framework to prohibit intermittent misclassifications. In the case study, we implement the framework to perform machine-part interaction classification on a milling machine, and the performance is evaluated using a testing dataset and deployment simulations. The implementation achieved an average F1-Score of 0.946 across classes on the testing dataset and an average delay of 0.24 seconds on the deployment simulations.

arXiv:2112.04461공식 코드 · Papers with Code

Enhancing Counterfactual Classification via Self-Training

Unlike traditional supervised learning, in many settings only partial feedback is available. We may only observe outcomes for the chosen actions, but not the counterfactual outcomes associated with other alternatives. Such settings encompass a wide variety of applications including pricing, online marketing and precision medicine. A key challenge is that observational data are influenced by historical policies deployed in the system, yielding a biased data distribution. We approach this task as a domain adaptation problem and propose a self-training algorithm which imputes outcomes with categorical values for finite unseen actions in the observational data to simulate a randomized trial through pseudolabeling, which we refer to as Counterfactual Self-Training (CST). CST iteratively imputes pseudolabels and retrains the model. In addition, we show input consistency loss can further improve CST performance which is shown in recent theoretical analysis of pseudolabeling. We demonstrate the effectiveness of the proposed algorithms on both synthetic and real datasets.

arXiv:2112.04182공식 코드 · Papers with Code

Unimodal Face Classification with Multimodal Training

Face recognition is a crucial task in various multimedia applications such as security check, credential access and motion sensing games. However, the task is challenging when an input face is noisy (e.g. poor-condition RGB image) or lacks certain information (e.g. 3D face without color). In this work, we propose a Multimodal Training Unimodal Test (MTUT) framework for robust face classification, which exploits the cross-modality relationship during training and applies it as a complementary of the imperfect single modality input during testing. Technically, during training, the framework (1) builds both intra-modality and cross-modality autoencoders with the aid of facial attributes to learn latent embeddings as multimodal descriptors, (2) proposes a novel multimodal embedding divergence loss to align the heterogeneous features from different modalities, which also adaptively avoids the useless modality (if any) from confusing the model. This way, the learned autoencoders can generate robust embeddings in single-modality face classification on test stage. We evaluate our framework in two face classification datasets and two kinds of testing input: (1) poor-condition image and (2) point cloud or 3D face mesh, when both 2D and 3D modalities are available for training. We experimentally show that our MTUT framework consistently outperforms ten baselines on 2D and 3D settings of both datasets.

arXiv:2112.03951

Few-Shot Image Classification Along Sparse Graphs

Few-shot learning remains a challenging problem, with unsatisfactory 1-shot accuracies for most real-world data. Here, we present a different perspective for data distributions in the feature space of a deep network and show how to exploit it for few-shot learning. First, we observe that nearest neighbors in the feature space are with high probability members of the same class while generally two random points from one class are not much closer to each other than points from different classes. This observation suggests that classes in feature space form sparse, loosely connected graphs instead of dense clusters. To exploit this property, we propose using a small amount of label propagation into the unlabeled space and then using a kernel PCA reconstruction error as decision boundary for the feature-space data distribution of each class. Using this method, which we call "K-Prop," we demonstrate largely improved few-shot learning performances (e.g., 83% accuracy for 1-shot 5-way classification on the RESISC45 satellite-images dataset) for datasets for which a backbone network can be trained with high within-class nearest-neighbor probabilities. We demonstrate this relationship using six different datasets.

arXiv:2112.03911공식 코드 · Papers with Code

Dyadic Sex Composition and Task Classification Using fNIRS Hyperscanning Data

Hyperscanning with functional near-infrared spectroscopy (fNIRS) is an emerging neuroimaging application that measures the nuanced neural signatures underlying social interactions. Researchers have assessed the effect of sex and task type (e.g., cooperation versus competition) on inter-brain coherence during human-to-human interactions. However, no work has yet used deep learning-based approaches to extract insights into sex and task-based differences in an fNIRS hyperscanning context. This work proposes a convolutional neural network-based approach to dyadic sex composition and task classification for an extensive hyperscanning dataset with $N = 222$ participants. Inter-brain signal similarity computed using dynamic time warping is used as the input data. The proposed approach achieves a maximum classification accuracy of greater than $80$ percent, thereby providing a new avenue for exploring and understanding complex brain behavior.

arXiv:2112.03622

Evaluating Generic Auto-ML Tools for Computational Pathology

Image analysis tasks in computational pathology are commonly solved using convolutional neural networks (CNNs). The selection of a suitable CNN architecture and hyperparameters is usually done through exploratory iterative optimization, which is computationally expensive and requires substantial manual work. The goal of this article is to evaluate how generic tools for neural network architecture search and hyperparameter optimization perform for common use cases in computational pathology. For this purpose, we evaluated one on-premises and one cloud-based tool for three different classification tasks for histological images: tissue classification, mutation prediction, and grading. We found that the default CNN architectures and parameterizations of the evaluated AutoML tools already yielded classification performance on par with the original publications. Hyperparameter optimization for these tasks did not substantially improve performance, despite the additional computational effort. However, performance varied substantially between classifiers obtained from individual AutoML runs due to non-deterministic effects. Generic CNN architectures and AutoML tools could thus be a viable alternative to manually optimizing CNN architectures and parametrizations. This would allow developers of software solutions for computational pathology to focus efforts on harder-to-automate tasks such as data curation.

arXiv:2112.03340공식 코드 · Papers with Code

Label Hallucination for Few-Shot Classification

Few-shot classification requires adapting knowledge learned from a large annotated base dataset to recognize novel unseen classes, each represented by few labeled examples. In such a scenario, pretraining a network with high capacity on the large dataset and then finetuning it on the few examples causes severe overfitting. At the same time, training a simple linear classifier on top of "frozen" features learned from the large labeled dataset fails to adapt the model to the properties of the novel classes, effectively inducing underfitting. In this paper we propose an alternative approach to both of these two popular strategies. First, our method pseudo-labels the entire large dataset using the linear classifier trained on the novel classes. This effectively "hallucinates" the novel classes in the large dataset, despite the novel categories not being present in the base database (novel and base classes are disjoint). Then, it finetunes the entire model with a distillation loss on the pseudo-labeled base examples, in addition to the standard cross-entropy loss on the novel dataset. This step effectively trains the network to recognize contextual and appearance cues that are useful for the novel-category recognition but using the entire large-scale base dataset and thus overcoming the inherent data-scarcity problem of few-shot learning. Despite the simplicity of the approach, we show that that our method outperforms the state-of-the-art on four well-established few-shot classification benchmarks.

arXiv:2112.03723

Shrub Ensembles for Online Classification

Online learning algorithms have become a ubiquitous tool in the machine learning toolbox and are frequently used in small, resource-constraint environments. Among the most successful online learning methods are Decision Tree (DT) ensembles. DT ensembles provide excellent performance while adapting to changes in the data, but they are not resource efficient. Incremental tree learners keep adding new nodes to the tree but never remove old ones increasing the memory consumption over time. Gradient-based tree learning, on the other hand, requires the computation of gradients over the entire tree which is costly for even moderately sized trees. In this paper, we propose a novel memory-efficient online classification ensemble called shrub ensembles for resource-constraint systems. Our algorithm trains small to medium-sized decision trees on small windows and uses stochastic proximal gradient descent to learn the ensemble weights of these `shrubs'. We provide a theoretical analysis of our algorithm and include an extensive discussion on the behavior of our approach in the online setting. In a series of 2~959 experiments on 12 different datasets, we compare our method against 8 state-of-the-art methods. Our Shrub Ensembles retain an excellent performance even when only little memory is available. We show that SE offers a better accuracy-memory trade-off in 7 of 12 cases, while having a statistically significant better performance than most other methods. Our implementation is available under https://github.com/sbuschjaeger/se-online .

arXiv:2112.03694공식 코드 · Papers with Code

Hard Sample Aware Noise Robust Learning for Histopathology Image Classification

Deep learning-based histopathology image classification is a key technique to help physicians in improving the accuracy and promptness of cancer diagnosis. However, the noisy labels are often inevitable in the complex manual annotation process, and thus mislead the training of the classification model. In this work, we introduce a novel hard sample aware noise robust learning method for histopathology image classification. To distinguish the informative hard samples from the harmful noisy ones, we build an easy/hard/noisy (EHN) detection model by using the sample training history. Then we integrate the EHN into a self-training architecture to lower the noise rate through gradually label correction. With the obtained almost clean dataset, we further propose a noise suppressing and hard enhancing (NSHE) scheme to train the noise robust model. Compared with the previous works, our method can save more clean samples and can be directly applied to the real-world noisy dataset scenario without using a clean subset. Experimental results demonstrate that the proposed scheme outperforms the current state-of-the-art methods in both the synthetic and real-world noisy datasets. The source code and data are available at https://github.com/bupt-ai-cz/HSA-NRL/.

arXiv:2112.02995공식 코드 · Papers with Code

TaskDrop: A Competitive Baseline for Continual Learning of Sentiment Classification

In this paper, we study the multi-task sentiment classification problem in the continual learning setting, i.e., a model is sequentially trained to classifier the sentiment of reviews of products in a particular category. The use of common sentiment words in reviews of different product categories leads to large cross-task similarity, which differentiates it from continual learning in other domains. This knowledge sharing nature renders forgetting reduction focused approaches less effective for the problem under consideration. Unlike existing approaches, where task-specific masks are learned with specifically presumed training objectives, we propose an approach called Task-aware Dropout (TaskDrop) to generate masks in a random way. While the standard dropout generates and applies random masks for each training instance per epoch for effective regularization, TaskDrop applies random masking for task-wise capacity allocation and reuse. We conducted experimental studies on three multi-task review datasets and made comparison to various baselines and state-of-the-art approaches. Our empirical results show that regardless of simplicity, TaskDrop overall achieved competitive performances for all the three datasets, especially after relative long term learning. This demonstrates that the proposed random capacity allocation mechanism works well for continual sentiment classification.

arXiv:2112.02301

Adaptive label thresholding methods for online multi-label classification

Existing online multi-label classification works cannot well handle the online label thresholding problem and lack the regret analysis for their online algorithms. This paper proposes a novel framework of adaptive label thresholding algorithms for online multi-label classification, with the aim to overcome the drawbacks of existing methods. The key feature of our framework is that both scoring and thresholding models are included as important components of the online multi-label classifier and are incorporated into one online optimization problem. Further, in order to establish the relationship between scoring and thresholding models, a novel multi-label classification loss function is derived, which measures to what an extent the multi-label classifier can distinguish between relevant labels and irrelevant ones for an incoming instance. Based on this new framework and loss function, we present a first-order linear algorithm and a second-order one, which both enjoy closed form update, but rely on different techniques for updating the multi-label classifier. Both algorithms are proved to achieve a sub-linear regret. Using Mercer kernels, our first-order algorithm has been extended to deal with nonlinear multi-label prediction tasks. Experiments show the advantage of our linear and nonlinear algorithms, in terms of various multi-label performance metrics.