PyTorchKR Papers

최신 논문

총 11,126편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2109.12969공식 코드 · Papers with Code

Challenging the Semi-Supervised VAE Framework for Text Classification

Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSVAEs for the task of text classification as we exhibit two sources of overcomplexity for which we provide simplifications. These simplifications to SSVAEs preserve their theoretical soundness while providing a number of practical advantages in the semi-supervised setup where the result of training is a text classifier. These simplifications are the removal of (i) the Kullback-Liebler divergence from its objective and (ii) the fully unobserved latent variable from its probabilistic model. These changes relieve users from choosing a prior for their latent variables, make the model smaller and faster, and allow for a better flow of information into the latent variables. We compare the simplified versions to standard SSVAEs on 4 text classification tasks. On top of the above-mentioned simplification, experiments show a speed-up of 26%, while keeping equivalent classification scores. The code to reproduce our experiments is public.

arXiv:2109.12176

On the Fairness of Swarm Learning in Skin Lesion Classification

in healthcare. However, the existing AI model may be biased in its decision marking. The bias induced by data itself, such as collecting data in subgroups only, can be mitigated by including more diversified data. Distributed and collaborative learning is an approach to involve training models in massive, heterogeneous, and distributed data sources, also known as nodes. In this work, we target on examining the fairness issue in Swarm Learning (SL), a recent edge-computing based decentralized machine learning approach, which is designed for heterogeneous illnesses detection in precision medicine. SL has achieved high performance in clinical applications, but no attempt has been made to evaluate if SL can improve fairness. To address the problem, we present an empirical study by comparing the fairness among single (node) training, SL, centralized training. Specifically, we evaluate on large public available skin lesion dataset, which contains samples from various subgroups. The experiments demonstrate that SL does not exacerbate the fairness problem compared to centralized training and improves both performance and fairness compared to single training. However, there still exists biases in SL model and the implementation of SL is more complex than the alternative two strategies.

arXiv:2109.12548공식 코드 · Papers with Code

Disentangled Feature Representation for Few-shot Image Classification

Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks as being distracted by the excursive features such as the background, domain and style of the image samples. In this work, we propose a novel Disentangled Feature Representation framework, dubbed DFR, for few-shot learning applications. DFR can adaptively decouple the discriminative features that are modeled by the classification branch, from the class-irrelevant component of the variation branch. In general, most of the popular deep few-shot learning methods can be plugged in as the classification branch, thus DFR can boost their performance on various few-shot tasks. Furthermore, we propose a novel FS-DomainNet dataset based on DomainNet, for benchmarking the few-shot domain generalization tasks. We conducted extensive experiments to evaluate the proposed DFR on general and fine-grained few-shot classification, as well as few-shot domain generalization, using the corresponding four benchmarks, i.e., mini-ImageNet, tiered-ImageNet, CUB, as well as the proposed FS-DomainNet. Thanks to the effective feature disentangling, the DFR-based few-shot classifiers achieved the state-of-the-art results on all datasets.

arXiv:2109.12431

Contrastive Unpaired Translation using Focal Loss for Patch Classification

Image-to-image translation models transfer images from input domain to output domain in an endeavor to retain the original content of the image. Contrastive Unpaired Translation is one of the existing methods for solving such problems. Significant advantage of this method, compared to competitors, is the ability to train and perform well in cases where both input and output domains are only a single image. Another key thing that differentiates this method from its predecessors is the usage of image patches rather than the whole images. It also turns out that sampling negatives (patches required to calculate the loss) from the same image achieves better results than a scenario where the negatives are sampled from other images in the dataset. This type of approach encourages mapping of corresponding patches to the same location in relation to other patches (negatives) while at the same time improves the output image quality and significantly decreases memory usage as well as the time required to train the model compared to CycleGAN method used as a baseline. Through a series of experiments we show that using focal loss in place of cross-entropy loss within the PatchNCE loss can improve on the model's performance and even surpass the current state-of-the-art model for image-to-image translation.

arXiv:2109.12261공식 코드 · Papers with Code

An embarrassingly simple comparison of machine learning algorithms for indoor scene classification

With the emergence of autonomous indoor robots, the computer vision task of indoor scene recognition has gained the spotlight. Indoor scene recognition is a challenging problem in computer vision that relies on local and global features in a scene. This study aims to compare the performance of five machine learning algorithms on the task of indoor scene classification to identify the pros and cons of each classifier. It also provides a comparison of low latency feature extractors versus enormous feature extractors to understand the performance effects. Finally, a simple MnasNet based indoor classification system is proposed, which can achieve 72% accuracy at 23 ms latency.

arXiv:2109.11577공식 코드 · Papers with Code

Text Ranking and Classification using Data Compression

A well-known but rarely used approach to text categorization uses conditional entropy estimates computed using data compression tools. Text affinity scores derived from compressed sizes can be used for classification and ranking tasks, but their success depends on the compression tools used. We use the Zstandard compressor and strengthen these ideas in several ways, calling the resulting language-agnostic technique Zest. In applications, this approach simplifies configuration, avoiding careful feature extraction and large ML models. Our ablation studies confirm the value of individual enhancements we introduce. We show that Zest complements and can compete with language-specific multidimensional content embeddings in production, but cannot outperform other counting methods on public datasets.

arXiv:2109.12040

From images in the wild to video-informed image classification

Image classifiers work effectively when applied on structured images, yet they often fail when applied on images with very high visual complexity. This paper describes experiments applying state-of-the-art object classifiers toward a unique set of images in the wild with high visual complexity collected on the island of Bali. The text describes differences between actual images in the wild and images from Imagenet, and then discusses a novel approach combining informational cues particular to video with an ensemble of imperfect classifiers in order to improve classification results on video sourced images of plants in the wild.

arXiv:2109.12026

Description-based Label Attention Classifier for Explainable ICD-9 Classification

ICD-9 coding is a relevant clinical billing task, where unstructured texts with information about a patient's diagnosis and treatments are annotated with multiple ICD-9 codes. Automated ICD-9 coding is an active research field, where CNN- and RNN-based model architectures represent the state-of-the-art approaches. In this work, we propose a description-based label attention classifier to improve the model explainability when dealing with noisy texts like clinical notes. We evaluate our proposed method with different transformer-based encoders on the MIMIC-III-50 dataset. Our method achieves strong results together with augmented explainablilty.

arXiv:2109.11891

Tackling Inter-Class Similarity and Intra-Class Variance for Microscopic Image-based Classification

Automatic classification of aquatic microorganisms is based on the morphological features extracted from individual images. The current works on their classification do not consider the inter-class similarity and intra-class variance that causes misclassification. We are particularly interested in the case where variance within a class occurs due to discrete visual changes in microscopic images. In this paper, we propose to account for it by partitioning the classes with high variance based on the visual features. Our algorithm automatically decides the optimal number of sub-classes to be created and consider each of them as a separate class for training. This way, the network learns finer-grained visual features. Our experiments on two databases of freshwater benthic diatoms and marine plankton show that our method can outperform the state-of-the-art approaches for classification of these aquatic microorganisms.

arXiv:2109.11282

Unbiased Loss Functions for Multilabel Classification with Missing Labels

This paper considers binary and multilabel classification problems in a setting where labels are missing independently and with a known rate. Missing labels are a ubiquitous phenomenon in extreme multi-label classification (XMC) tasks, such as matching Wikipedia articles to a small subset out of the hundreds of thousands of possible tags, where no human annotator can possibly check the validity of all the negative samples. For this reason, propensity-scored precision -- an unbiased estimate for precision-at-k under a known noise model -- has become one of the standard metrics in XMC. Few methods take this problem into account already during the training phase, and all are limited to loss functions that can be decomposed into a sum of contributions from each individual label. A typical approach to training is to reduce the multilabel problem into a series of binary or multiclass problems, and it has been shown that if the surrogate task should be consistent for optimizing recall, the resulting loss function is not decomposable over labels. Therefore, this paper derives the unique unbiased estimators for the different multilabel reductions, including the non-decomposable ones. These estimators suffer from increased variance and may lead to ill-posed optimization problems, which we address by switching to convex upper-bounds. The theoretical considerations are further supplemented by an experimental study showing that the switch to unbiased estimators significantly alters the bias-variance trade-off and may thus require stronger regularization, which in some cases can negate the benefits of unbiased estimation.

arXiv:2109.11406

Named Entity Recognition and Classification on Historical Documents: A Survey

After decades of massive digitisation, an unprecedented amount of historical documents is available in digital format, along with their machine-readable texts. While this represents a major step forward with respect to preservation and accessibility, it also opens up new opportunities in terms of content mining and the next fundamental challenge is to develop appropriate technologies to efficiently search, retrieve and explore information from this 'big data of the past'. Among semantic indexing opportunities, the recognition and classification of named entities are in great demand among humanities scholars. Yet, named entity recognition (NER) systems are heavily challenged with diverse, historical and noisy inputs. In this survey, we present the array of challenges posed by historical documents to NER, inventory existing resources, describe the main approaches deployed so far, and identify key priorities for future developments.

arXiv:2109.10856

Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data

Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we introduce a new problem called coarse-to-fine grained classification, which aims to perform fine-grained classification on coarsely annotated data. Instead of asking for new fine-grained human annotations, we opt to leverage label surface names as the only human guidance and weave in rich pre-trained generative language models into the iterative weak supervision strategy. Specifically, we first propose a label-conditioned finetuning formulation to attune these generators for our task. Furthermore, we devise a regularization objective based on the coarse-fine label constraints derived from our problem setting, giving us even further improvements over the prior formulation. Our framework uses the fine-tuned generative models to sample pseudo-training data for training the classifier, and bootstraps on real unlabeled data for model refinement. Extensive experiments and case studies on two real-world datasets demonstrate superior performance over SOTA zero-shot classification baselines.

arXiv:2109.10855

BFClass: A Backdoor-free Text Classification Framework

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers, however, defending such attacks remains an open problem. In this work, we propose BFClass, a novel efficient backdoor-free training framework for text classification. The backbone of BFClass is a pre-trained discriminator that predicts whether each token in the corrupted input was replaced by a masked language model. To identify triggers, we utilize this discriminator to locate the most suspicious token from each training sample and then distill a concise set by considering their association strengths with particular labels. To recognize the poisoned subset, we examine the training samples with these identified triggers as the most suspicious token, and check if removing the trigger will change the poisoned model's prediction. Extensive experiments demonstrate that BFClass can identify all the triggers, remove 95% poisoned training samples with very limited false alarms, and achieve almost the same performance as the models trained on the benign training data.

arXiv:2109.10623

Sharp Analysis of Random Fourier Features in Classification

We study the theoretical properties of random Fourier features classification with Lipschitz continuous loss functions such as support vector machine and logistic regression. Utilizing the regularity condition, we show for the first time that random Fourier features classification can achieve $O(1/\sqrt{n})$ learning rate with only $\Omega(\sqrt{n} \log n)$ features, as opposed to $\Omega(n)$ features suggested by previous results. Our study covers the standard feature sampling method for which we reduce the number of features required, as well as a problem-dependent sampling method which further reduces the number of features while still keeping the optimal generalization property. Moreover, we prove that the random Fourier features classification can obtain a fast $O(1/n)$ learning rate for both sampling schemes under Massart's low noise assumption. Our results demonstrate the potential effectiveness of random Fourier features approximation in reducing the computational complexity (roughly from $O(n^3)$ in time and $O(n^2)$ in space to $O(n^2)$ and $O(n\sqrt{n})$ respectively) without having to trade-off the statistical prediction accuracy. In addition, the achieved trade-off in our analysis is at least the same as the optimal results in the literature under the worst case scenario and significantly improves the optimal results under benign regularity conditions.

arXiv:2109.10436

Classification with Nearest Disjoint Centroids

In this paper, we develop a new classification method based on nearest centroid, and it is called the nearest disjoint centroid classifier. Our method differs from the nearest centroid classifier in the following two aspects: (1) the centroids are defined based on disjoint subsets of features instead of all the features, and (2) the distance is induced by the dimensionality-normalized norm instead of the Euclidean norm. We provide a few theoretical results regarding our method. In addition, we propose a simple algorithm based on adapted k-means clustering that can find the disjoint subsets of features used in our method, and extend the algorithm to perform feature selection. We evaluate and compare the performance of our method to other classification methods on both simulated data and real-world gene expression datasets. The results demonstrate that our method is able to outperform other competing classifiers by having smaller misclassification rates and/or using fewer features in various settings and situations.

arXiv:2109.09988

Signal Classification using Smooth Coefficients of Multiple wavelets

Classification of time series signals has become an important construct and has many practical applications. With existing classifiers we may be able to accurately classify signals, however that accuracy may decline if using a reduced number of attributes. Transforming the data then undertaking reduction in dimensionality may improve the quality of the data analysis, decrease time required for classification and simplify models. We propose an approach, which chooses suitable wavelets to transform the data, then combines the output from these transforms to construct a dataset to then apply ensemble classifiers to. We demonstrate this on different data sets, across different classifiers and use differing evaluation methods. Our experimental results demonstrate the effectiveness of the proposed technique, compared to the approaches that use either raw signal data or a single wavelet transform.

arXiv:2109.09883공식 코드 · Papers with Code

On the Importance of Distractors for Few-Shot Classification

Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples. An effective approach to few-shot classification involves a prior model trained on a large-sample base domain, which is then finetuned over the novel few-shot task to yield generalizable representations. However, task-specific finetuning is prone to overfitting due to the lack of enough training examples. To alleviate this issue, we propose a new finetuning approach based on contrastive learning that reuses unlabelled examples from the base domain in the form of distractors. Unlike the nature of unlabelled data used in prior works, distractors belong to classes that do not overlap with the novel categories. We demonstrate for the first time that inclusion of such distractors can significantly boost few-shot generalization. Our technical novelty includes a stochastic pairing of examples sharing the same category in the few-shot task and a weighting term that controls the relative influence of task-specific negatives and distractors. An important aspect of our finetuning objective is that it is agnostic to distractor labels and hence applicable to various base domain settings. Compared to state-of-the-art approaches, our method shows accuracy gains of up to $12\%$ in cross-domain and up to $5\%$ in unsupervised prior-learning settings.

arXiv:2109.09850공식 코드 · Papers with Code

Balanced-MixUp for Highly Imbalanced Medical Image Classification

Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases, typically resulting in poor performance of machine learning algorithms due to overfitting in the learning process. In this paper, we propose a novel mechanism for sampling training data based on the popular MixUp regularization technique, which we refer to as Balanced-MixUp. In short, Balanced-MixUp simultaneously performs regular (i.e., instance-based) and balanced (i.e., class-based) sampling of the training data. The resulting two sets of samples are then mixed-up to create a more balanced training distribution from which a neural network can effectively learn without incurring in heavily under-fitting the minority classes. We experiment with a highly imbalanced dataset of retinal images (55K samples, 5 classes) and a long-tail dataset of gastro-intestinal video frames (10K images, 23 classes), using two CNNs of varying representation capabilities. Experimental results demonstrate that applying Balanced-MixUp outperforms other conventional sampling schemes and loss functions specifically designed to deal with imbalanced data. Code is released at https://github.com/agaldran/balanced_mixup .

arXiv:2109.09796공식 코드 · Papers with Code

Transforming Fake News: Robust Generalisable News Classification Using Transformers

As online news has become increasingly popular and fake news increasingly prevalent, the ability to audit the veracity of online news content has become more important than ever. Such a task represents a binary classification challenge, for which transformers have achieved state-of-the-art results. Using the publicly available ISOT and Combined Corpus datasets, this study explores transformers' abilities to identify fake news, with particular attention given to investigating generalisation to unseen datasets with varying styles, topics and class distributions. Moreover, we explore the idea that opinion-based news articles cannot be classified as real or fake due to their subjective nature and often sensationalised language, and propose a novel two-step classification pipeline to remove such articles from both model training and the final deployed inference system. Experiments over the ISOT and Combined Corpus datasets show that transformers achieve an increase in F1 scores of up to 4.9% for out of distribution generalisation compared to baseline approaches, with a further increase of 10.1% following the implementation of our two-step classification pipeline. To the best of our knowledge, this study is the first to investigate generalisation of transformers in this context.

arXiv:2109.09777공식 코드 · Papers with Code

DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection

This paper describes our submission to the DISRPT2021 Shared Task on Discourse Unit Segmentation, Connective Detection, and Relation Classification. Our system, called DisCoDisCo, is a Transformer-based neural classifier which enhances contextualized word embeddings (CWEs) with hand-crafted features, relying on tokenwise sequence tagging for discourse segmentation and connective detection, and a feature-rich, encoder-less sentence pair classifier for relation classification. Our results for the first two tasks outperform SOTA scores from the previous 2019 shared task, and results on relation classification suggest strong performance on the new 2021 benchmark. Ablation tests show that including features beyond CWEs are helpful for both tasks, and a partial evaluation of multiple pre-trained Transformer-based language models indicates that models pre-trained on the Next Sentence Prediction (NSP) task are optimal for relation classification.