One-class classification (OCC), which models one single positive class and distinguishes it from the negative class, has been a long-standing topic with pivotal application to realms like anomaly detection. As modern society often deals with massive high-dimensional complex data spawned by multiple sources, it is natural to consider OCC from the perspective of multi-view deep learning. However, it has not been discussed by the literature and remains an unexplored topic. Motivated by this blank, this paper makes four-fold contributions: First, to our best knowledge, this is the first work that formally identifies and formulates the multi-view deep OCC problem. Second, we take recent advances in relevant areas into account and systematically devise eleven different baseline solutions for multi-view deep OCC, which lays the foundation for research on multi-view deep OCC. Third, to remedy the problem that limited benchmark datasets are available for multi-view deep OCC, we extensively collect existing public data and process them into more than 30 new multi-view benchmark datasets via multiple means, so as to provide a publicly available evaluation platform for multi-view deep OCC. Finally, by comprehensively evaluating the devised solutions on benchmark datasets, we conduct a thorough analysis on the effectiveness of the designed baselines, and hopefully provide other researchers with beneficial guidance and insight to multi-view deep OCC. Our data and codes are opened at https://github.com/liujiyuan13/MvDOCC-datasets and https://github.com/liujiyuan13/MvDOCC-code respectively to facilitate future research.
Content-based music information retrieval has seen rapid progress with the adoption of deep learning. Current approaches to high-level music description typically make use of classification models, such as in auto-tagging or genre and mood classification. In this work, we propose to address music description via audio captioning, defined as the task of generating a natural language description of music audio content in a human-like manner. To this end, we present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convolutional and recurrent neural network architectures to jointly process audio-text inputs through a multimodal encoder and leverages pre-training on audio data to obtain representations that effectively capture and summarise musical features in the input. Evaluation of the generated captions through automatic metrics shows that our method outperforms a baseline designed for non-music audio captioning. Through an ablation study, we unveil that this performance boost can be mainly attributed to pre-training of the audio encoder, while other design choices - modality fusion, decoding strategy and the use of attention - contribute only marginally. Our model represents a shift away from classification-based music description and combines tasks requiring both auditory and linguistic understanding to bridge the semantic gap in music information retrieval.
Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the existing system with limited labeled data. The system should be intelligent enough to recognize upcoming new classes with a few examples. In this work, we define a new task in the NLP domain, incremental few-shot text classification, where the system incrementally handles multiple rounds of new classes. For each round, there is a batch of new classes with a few labeled examples per class. Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes. In addition to formulating the new task, we also release two benchmark datasets in the incremental few-shot setting: intent classification and relation classification. Moreover, we propose two entailment approaches, ENTAILMENT and HYBRID, which show promise for solving this novel problem.
Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and learning speed due to the hard labels and non-uniform distribution over labels. Several regularization techniques have been used to overcome the aforesaid issues. However, sometimes models learn to predict the samples extremely confidently which is not good from a generalization point of view. Therefore, this paper proposed an idea to enhance the generalization performance of a hybrid CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that in improving generalization performance, label smoothing also improves model calibration which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation which reveals improved generalization performance, statistical significance, and computational complexity as compared to the state-of-the-art models. The code will be made available at https://github.com/mahmad00.
Object Detection is the task of classification and localization of objects in an image or video. It has gained prominence in recent years due to its widespread applications. This article surveys recent developments in deep learning based object detectors. Concise overview of benchmark datasets and evaluation metrics used in detection is also provided along with some of the prominent backbone architectures used in recognition tasks. It also covers contemporary lightweight classification models used on edge devices. Lastly, we compare the performances of these architectures on multiple metrics.
Understanding complex scenarios from in-vehicle cameras is essential for safely operating autonomous driving systems in densely populated areas. Among these, intersection areas are one of the most critical as they concentrate a considerable number of traffic accidents and fatalities. Detecting and understanding the scene configuration of these usually crowded areas is then of extreme importance for both autonomous vehicles and modern ADAS aimed at preventing road crashes and increasing the safety of vulnerable road users. This work investigates inter-section classification from RGB images using well-consolidate neural network approaches along with a method to enhance the results based on the teacher/student training paradigm. An extensive experimental activity aimed at identifying the best input configuration and evaluating different network parameters on both the well-known KITTI dataset and the new KITTI-360 sequences shows that our method outperforms current state-of-the-art approaches on a per-frame basis and prove the effectiveness of the proposed learning scheme.
One of the main challenges since the advancement of convolutional neural networks is how to connect the extracted feature map to the final classification layer. VGG models used two sets of fully connected layers for the classification part of their architectures, which significantly increased the number of models' weights. ResNet and the next deep convolutional models used the Global Average Pooling (GAP) layer to compress the feature map and feed it to the classification layer. Although using the GAP layer reduces the computational cost, but also causes losing spatial resolution of the feature map, which results in decreasing learning efficiency. In this paper, we aim to tackle this problem by replacing the GAP layer with a new architecture called Wise-SrNet. It is inspired by the depthwise convolutional idea and is designed for processing spatial resolution while not increasing computational cost. We have evaluated our method using three different datasets: Intel Image Classification Challenge, MIT Indoors Scenes, and a part of the ImageNet dataset. We investigated the implementation of our architecture on several models of the Inception, ResNet, and DenseNet families. Applying our architecture has revealed a significant effect on increasing convergence speed and accuracy. Our Experiments on images with 224*224 resolution increased the Top-1 accuracy between 2% to 8% on different datasets and models. Running our models on 512*512 resolution images of the MIT Indoors Scenes dataset showed a notable result of improving the Top-1 accuracy within 3% to 26%. We will also demonstrate the GAP layer's disadvantage when the input images are large and the number of classes is not few. In this circumstance, our proposed architecture can do a great help in enhancing classification results. The code is shared at https://github.com/mr7495/image-classification-spatial.
Text classification has seen an increased use in both academic and industry settings. Though rule based methods have been fairly successful, supervised machine learning has been shown to be most successful for most languages, where most research was done on English. In this article, the success of lexicon analysis, support vector machines, and extreme gradient boosting for the task of text classification and sentiment analysis are evaluated in Turkish and a pretrained transformer based classifier is proposed, outperforming previous methods for Turkish text classification. In the context of text classification, all machine learning models proposed in the article are domain-independent and do not require any task-specific modifications.
Decades of research suggest that information exchange in groups and organizations can reliably improve judgment accuracy in tasks such as financial forecasting, market research, and medical decision-making. However, we show that improving the accuracy of numeric estimates does not necessarily improve the accuracy of decisions. For binary choice judgments, also known as classification tasks--e.g. yes/no or build/buy decisions--social influence is most likely to grow the majority vote share, regardless of the accuracy of that opinion. As a result, initially inaccurate groups become increasingly inaccurate after information exchange even as they signal stronger support. We term this dynamic the "crowd classification problem." Using both a novel dataset as well as a reanalysis of three previous datasets, we study this process in two types of information exchange: (1) when people share votes only, and (2) when people form and exchange numeric estimates prior to voting. Surprisingly, when people exchange numeric estimates prior to voting, the binary choice vote can become less accurate even as the average numeric estimate becomes more accurate. Our findings recommend against voting as a form of decision-making when groups are optimizing for accuracy. For those cases where voting is required, we discuss strategies for managing communication to avoid the crowd classification problem. We close with a discussion of how our results contribute to a broader contingency theory of collective intelligence.
In some memory-constrained settings like IoT devices and over-the-network data pipelines, it can be advantageous to have smaller contextual embeddings. We investigate the efficacy of projecting contextual embedding data (BERT) onto a manifold, and using nonlinear dimensionality reduction techniques to compress these embeddings. In particular, we propose a novel post-processing approach, applying a combination of Isomap and PCA. We find that the geodesic distance estimations, estimates of the shortest path on a Riemannian manifold, from Isomap's k-Nearest Neighbors graph bolstered the performance of the compressed embeddings to be comparable to the original BERT embeddings. On one dataset, we find that despite a 12-fold dimensionality reduction, the compressed embeddings performed within 0.1% of the original BERT embeddings on a downstream classification task. In addition, we find that this approach works particularly well on tasks reliant on syntactic data, when compared with linear dimensionality reduction. These results show promise for a novel geometric approach to achieve lower dimensional text embeddings from existing transformers and pave the way for data-specific and application-specific embedding compressions.
Traditional breast cancer image classification methods require manual extraction of features from medical images, which not only require professional medical knowledge, but also have problems such as time-consuming and labor-intensive and difficulty in extracting high-quality features. Therefore, the paper proposes a computer-based feature fusion Convolutional neural network breast cancer image classification and detection method. The paper pre-trains two convolutional neural networks with different structures, and then uses the convolutional neural network to automatically extract the characteristics of features, fuse the features extracted from the two structures, and finally use the classifier classifies the fused features. The experimental results show that the accuracy of this method in the classification of breast cancer image data sets is 89%, and the classification accuracy of breast cancer images is significantly improved compared with traditional methods.
Synthetic aperture radar (SAR) is widely used for ground surface classification since it utilizes information on vegetation and soil unavailable in optical observation. Image classification often employs convolutional neural networks. However, they have serious problems such as long learning time and resolution degradation in their convolution and pooling processes. In this paper, we propose complex-valued reservoir computing (CVRC) to deal with complex-valued images in interferometric SAR (InSAR). We classify InSAR image data by using CVRC successfully with a higher resolution and a lower computational cost, i.e., one-hundredth learning time and one-fifth classification time, than convolutional neural networks. We also conduct experiments on slope angle estimation. CVRC is found applicable to quantitative tasks dealing with continuous values as well as discrete classification tasks with a higher accuracy.
Current intent classification approaches assign binary intent class memberships to natural language utterances while disregarding the inherent vagueness in language and the corresponding vagueness in intent class boundaries. In this work, we propose a scheme to address the ambiguity in single-intent as well as multi-intent natural language utterances by creating degree memberships over fuzzified intent classes. To our knowledge, this is the first work to address and quantify the impact of the fuzzy nature of natural language utterances over intent category memberships. Additionally, our approach overcomes the sparsity of multi-intent utterance data to train classification models by using a small database of single intent utterances to generate class memberships over multi-intent utterances. We evaluate our approach over two task-oriented dialog datasets, across different fuzzy membership generation techniques and approximate string similarity measures. Our results reveal the impact of lexical overlap between utterances of different intents, and the underlying data distributions, on the fuzzification of intent memberships. Moreover, we evaluate the accuracy of our approach by comparing the defuzzified memberships to their binary counterparts, across different combinations of membership functions and string similarity measures.
We introduce a new rule-based optimization method for classification with constraints. The proposed method leverages column generation for linear programming, and hence, is scalable to large datasets. The resulting pricing subproblem is shown to be NP-Hard. We recourse to a decision tree-based heuristic and solve a proxy pricing subproblem for acceleration. The method returns a set of rules along with their optimal weights indicating the importance of each rule for learning. We address interpretability and fairness by assigning cost coefficients to the rules and introducing additional constraints. In particular, we focus on local interpretability and generalize separation criterion in fairness to multiple sensitive attributes and classes. We test the performance of the proposed methodology on a collection of datasets and present a case study to elaborate on its different aspects. The proposed rule-based learning method exhibits a good compromise between local interpretability and fairness on the one side, and accuracy on the other side.
Recently the vision transformer (ViT) architecture, where the backbone purely consists of self-attention mechanism, has achieved very promising performance in visual classification. However, the high performance of the original ViT heavily depends on pretraining using ultra large-scale datasets, and it significantly underperforms on ImageNet-1K if trained from scratch. This paper makes the efforts toward addressing this problem, by carefully considering the role of visual tokens. First, for classification head, existing ViT only exploits class token while entirely neglecting rich semantic information inherent in high-level visual tokens. Therefore, we propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification. Meanwhile, a fast singular value power normalization is proposed for improving the second-order pooling. Second, the original ViT employs the naive embedding of fixed-size image patches, lacking the ability to model translation equivariance and locality. To alleviate this problem, we develop a light-weight, hierarchical module based on off-the-shelf convolutions for visual token embedding. The proposed architecture, which we call So-ViT, is thoroughly evaluated on ImageNet-1K. The results show our models, when trained from scratch, outperform the competing ViT variants, while being on par with or better than state-of-the-art CNN models. Code is available at https://github.com/jiangtaoxie/So-ViT
Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to semantically related unseen classes, which are absent during training. The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned on semantic side information and to incorporate meta-learning to eliminate the model's inherent bias towards seen classes. While existing meta generative approaches pursue a common model shared across task distributions, we aim to construct a generative network adaptive to task characteristics. To this end, we propose an Attribute-Modulated generAtive meta-model for Zero-shot learning (AMAZ). Our model consists of an attribute-aware modulation network, an attribute-augmented generative network, and an attribute-weighted classifier. Given unseen classes, the modulation network adaptively modulates the generator by applying task-specific transformations so that the generative network can adapt to highly diverse tasks. The weighted classifier utilizes the data quality to enhance the training procedure, further improving the model performance. Our empirical evaluations on four widely-used benchmarks show that AMAZ outperforms state-of-the-art methods by 3.8% and 3.1% in ZSL and generalized ZSL settings, respectively, demonstrating the superiority of our method. Our experiments on a zero-shot image retrieval task show AMAZ's ability to synthesize instances that portray real visual characteristics.
Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification.
Multi-label classification is a type of classification task, it is used when there are two or more classes, and the data point we want to predict may belong to none of the classes or all of them at the same time. In the real world, many applications are actually multi-label involved, including information retrieval, multimedia content annotation, web mining, and so on. A game theory-based framework known as SHapley Additive exPlanations (SHAP) has been applied to explain various supervised learning models without being aware of the exact model. Herein, this work further extends the explanation of multi-label classification task by using the SHAP methodology. The experiment demonstrates a comprehensive comparision of different algorithms on well known multi-label datasets and shows the usefulness of the interpretation.
We introduce a theoretical framework for understanding and predicting the complexity of sequence classification tasks, using a novel extension of the theory of Boolean function sensitivity. The sensitivity of a function, given a distribution over input sequences, quantifies the number of disjoint subsets of the input sequence that can each be individually changed to change the output. We argue that standard sequence classification methods are biased towards learning low-sensitivity functions, so that tasks requiring high sensitivity are more difficult. To that end, we show analytically that simple lexical classifiers can only express functions of bounded sensitivity, and we show empirically that low-sensitivity functions are easier to learn for LSTMs. We then estimate sensitivity on 15 NLP tasks, finding that sensitivity is higher on challenging tasks collected in GLUE than on simple text classification tasks, and that sensitivity predicts the performance both of simple lexical classifiers and of vanilla BiLSTMs without pretrained contextualized embeddings. Within a task, sensitivity predicts which inputs are hard for such simple models. Our results suggest that the success of massively pretrained contextual representations stems in part because they provide representations from which information can be extracted by low-sensitivity decoders.
Resting state functional magnetic resonance images (fMRI) are commonly used for classification of patients as having Alzheimer's disease (AD), mild cognitive impairment (MCI), or being cognitive normal (CN). Most methods use time-series correlation of voxels signals during the observation period as a basis for the classification. In this paper we show that Convolutional Neural Network (CNN) classification based on spatial correlation of time-averaged signals yield a classification accuracy of up to 82% (sensitivity 86%, specificity 80%)for a data set with 429 subjects (246 cognitive normal and 183 Alzheimer patients). For the spatial correlation of time-averaged signal values we use voxel subdomains around center points of the 90 regions AAL atlas. We form the subdomains as sets of voxels along a Hilbert curve of a bounding box in which the brain is embedded with the AAL regions center points serving as subdomain seeds. The matrix resulting from the spatial correlation of the 90 arrays formed by the subdomain segments of the Hilbert curve yields a symmetric 90x90 matrix that is used for the classification based on two different CNN networks, a 4-layer CNN network with 3x3 filters and with 4, 8, 16, and 32 output channels respectively, and a 2-layer CNN network with 3x3 filters and with 4 and 8 output channels respectively. The results of the two networks are reported and compared.