From crying to babbling and then to speech, infant's vocal tract goes through anatomic restructuring. In this paper, we propose a non-invasive fast method of using infant cry signals with convolutional neural network (CNN) based age classification to diagnose the abnormality of the vocal tract development as early as 4-month age. We study F0, F1, F2, and spectrograms and relate them to the postnatal development of infant vocalization. A novel CNN based age classification is performed with binary age pairs to discover the pattern and tendency of the vocal tract changes. The effectiveness of this approach is evaluated on Baby2020 with healthy infant cries and Baby Chillanto database with pathological infant cries. The results show that our approach yields 79.20% accuracy for healthy cries, 84.80% for asphyxiated cries, and 91.20% for deaf cries. Our method first reveals that infants' vocal tract develops to a certain level at 4-month age and infants can start controlling the vocal folds to produce discontinuous cry sounds leading to babbling. Early diagnosis of growth abnormality of the vocal tract can help parents keep vigilant and adopt medical treatment or training therapy for their infants as early as possible.
Random field and random cluster theory are used to describe certain mathematical results concerning the probability distribution of image pixel intensities characterized as generic $2D$ integer arrays. The size of the smallest bounded region within an image is estimated for segmenting an image, from which, the equilibrium distribution of intensities can be recovered. From the estimated bounded regions, properties of the sub-optimal and equilibrium distributions of intensities are derived, which leads to an image compression methodology whereby only slightly more than half of all pixels are required for a worst-case reconstruction of the original image. A custom deep belief network and heuristic allows for the unsupervised segmentation, detection and localization of objects in an image. An example illustrates the mathematical results.
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.
We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal representations that are rich enough to benefit a variety of downstream tasks. We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and text-to-video retrieval. Furthermore, we study a modality-agnostic, single-backbone Transformer by sharing weights among the three modalities. We show that the convolution-free VATT outperforms state-of-the-art ConvNet-based architectures in the downstream tasks. Especially, VATT's vision Transformer achieves the top-1 accuracy of 82.1% on Kinetics-400, 83.6% on Kinetics-600, 72.7% on Kinetics-700, and 41.1% on Moments in Time, new records while avoiding supervised pre-training. Transferring to image classification leads to 78.7% top-1 accuracy on ImageNet compared to 64.7% by training the same Transformer from scratch, showing the generalizability of our model despite the domain gap between videos and images. VATT's audio Transformer also sets a new record on waveform-based audio event recognition by achieving the mAP of 39.4% on AudioSet without any supervised pre-training. VATT's source code is publicly available.
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
In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional trainable class token, our proposed one takes advantage of all the image patch tokens to compute the training loss in a dense manner. Specifically, token labeling reformulates the image classification problem into multiple token-level recognition problems and assigns each patch token with an individual location-specific supervision generated by a machine annotator. Experiments show that token labeling can clearly and consistently improve the performance of various ViT models across a wide spectrum. For a vision transformer with 26M learnable parameters serving as an example, with token labeling, the model can achieve 84.4% Top-1 accuracy on ImageNet. The result can be further increased to 86.4% by slightly scaling the model size up to 150M, delivering the minimal-sized model among previous models (250M+) reaching 86%. We also show that token labeling can clearly improve the generalization capability of the pre-trained models on downstream tasks with dense prediction, such as semantic segmentation. Our code and all the training details will be made publicly available at https://github.com/zihangJiang/TokenLabeling.
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.
Two DL models were developed using radiograph-level annotations (yes or no disease) and fine-grained lesion-level annotations (lesion bounding boxes), respectively named CheXNet and CheXDet. The models' internal classification performance and lesion localization performance were compared on a testing set (n=2,922), external classification performance was compared on NIH-Google (n=4,376) and PadChest (n=24,536) datasets, and external lesion localization performance was compared on NIH-ChestX-ray14 dataset (n=880). The models were also compared to radiologists on a subset of the internal testing set (n=496). Given sufficient training data, both models performed comparably to radiologists. CheXDet achieved significant improvement for external classification, such as in classifying fracture on NIH-Google (CheXDet area under the ROC curve [AUC]: 0.67, CheXNet AUC: 0.51; p<.001) and PadChest (CheXDet AUC: 0.78, CheXNet AUC: 0.55; p<.001). CheXDet achieved higher lesion detection performance than CheXNet for most abnormalities on all datasets, such as in detecting pneumothorax on the internal set (CheXDet jacknife alternative free-response ROC-figure of merit [JAFROC-FOM]: 0.87, CheXNet JAFROC-FOM: 0.13; p<.001) and NIH-ChestX-ray14 (CheXDet JAFROC-FOM: 0.55, CheXNet JAFROC-FOM: 0.04; p<.001). To summarize, fine-grained annotations overcame shortcut learning and enabled DL models to identify correct lesion patterns, improving the models' generalizability.
With the fast growing demand on new services and applications as well as the increasing awareness of data protection, traditional centralized traffic classification approaches are facing unprecedented challenges. This paper introduces a novel framework, Federated Generative Adversarial Networks and Automatic Classification (FGAN-AC), which integrates decentralized data synthesizing with traffic classification. FGAN-AC is able to synthesize and classify multiple types of service data traffic from decentralized local datasets without requiring a large volume of manually labeled dataset or causing any data leakage. Two types of data synthesizing approaches have been proposed and compared: computation-efficient FGAN (FGAN-\uppercase\expandafter{\romannumeral1}) and communication-efficient FGAN (FGAN-\uppercase\expandafter{\romannumeral2}). The former only implements a single CNN model for processing each local dataset and the later only requires coordination of intermediate model training parameters. An automatic data classification and model updating framework has been proposed to automatically identify unknown traffic from the synthesized data samples and create new pseudo-labels for model training. Numerical results show that our proposed framework has the ability to synthesize highly mixed service data traffic and can significantly improve the traffic classification performance compared to existing solutions.
Subset selection is a valuable tool for interpretable learning, scientific discovery, and data compression. However, classical subset selection is often avoided due to selection instability, lack of regularization, and difficulties with post-selection inference. We address these challenges from a Bayesian perspective. Given any Bayesian predictive model $\mathcal{M}$, we extract a family of near-optimal subsets of variables for linear prediction or classification. This strategy deemphasizes the role of a single "best" subset and instead advances the broader perspective that often many subsets are highly competitive. The acceptable family of subsets offers a new pathway for model interpretation and is neatly summarized by key members such as the smallest acceptable subset, along with new (co-) variable importance metrics based on whether variables (co-) appear in all, some, or no acceptable subsets. More broadly, we apply Bayesian decision analysis to derive the optimal linear coefficients for any subset of variables. These coefficients inherit both regularization and predictive uncertainty quantification via $\mathcal{M}$. For both simulated and real data, the proposed approach exhibits better prediction, interval estimation, and variable selection than competing Bayesian and frequentist selection methods. These tools are applied to a large education dataset with highly correlated covariates. Our analysis provides unique insights into the combination of environmental, socioeconomic, and demographic factors that predict educational outcomes, and identifies over 200 distinct subsets of variables that offer near-optimal out-of-sample predictive accuracy.
We address the problem of unsupervised classification of players in a team sport according to their team affiliation, when jersey colours and design are not known a priori. We adopt a contrastive learning approach in which an embedding network learns to maximize the distance between representations of players on different teams relative to players on the same team, in a purely unsupervised fashion, without any labelled data. We evaluate the approach using a new hockey dataset and find that it outperforms prior unsupervised approaches by a substantial margin, particularly for real-time application when only a small number of frames are available for unsupervised learning before team assignments must be made. Remarkably, we show that our contrastive method achieves 94% accuracy after unsupervised training on only a single frame, with accuracy rising to 97% within 500 frames (17 seconds of game time). We further demonstrate how accurate team classification allows accurate team-conditional heat maps of player positioning to be computed.
Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular interest to these emerging standards is the development of learning-based image compression systems targeting both humans and machines. This paper is concerned with learning-based compression schemes whose compressed-domain representations can be utilized to perform visual processing and computer vision tasks directly in the compressed domain. Such a characteristic has been incorporated as part of the scope and requirements of the new emerging JPEG-AI standard. In our work, we adopt the learning-based JPEG-AI framework for performing material and texture recognition using the compressed-domain latent representation at varing bit-rates. For comparison, performance results are presented using compressed but fully decoded images in the pixel domain as well as original uncompressed images. The obtained performance results show that even though decoded images can degrade the classification performance of the model trained with original images, retraining the model with decoded images will largely reduce the performance gap for the adopted texture dataset. It is also shown that the compressed-domain classification can yield a competitive performance in terms of Top-1 and Top-5 accuracy while using a smaller reduced-complexity classification model.
Recently, there has been great success in applying deep neural networks on graph structured data. Most work, however, focuses on either node- or graph-level supervised learning, such as node, link or graph classification or node-level unsupervised learning (e.g. node clustering). Despite its wide range of possible applications, graph-level unsupervised learning has not received much attention yet. This might be mainly attributed to the high representation complexity of graphs, which can be represented by n! equivalent adjacency matrices, where n is the number of nodes. In this work we address this issue by proposing a permutation-invariant variational autoencoder for graph structured data. Our proposed model indirectly learns to match the node ordering of input and output graph, without imposing a particular node ordering or performing expensive graph matching. We demonstrate the effectiveness of our proposed model on various graph reconstruction and generation tasks and evaluate the expressive power of extracted representations for downstream graph-level classification and regression.
This paper describes our contribution to the WASSA 2021 shared task on Empathy Prediction and Emotion Classification. The broad goal of this task was to model an empathy score, a distress score and the overall level of emotion of an essay written in response to a newspaper article associated with harm to someone. We have used the ELECTRA model abundantly and also advanced deep learning approaches like multi-task learning. Additionally, we also leveraged standard machine learning techniques like ensembling. Our system achieves a Pearson Correlation Coefficient of 0.533 on sub-task I and a macro F1 score of 0.5528 on sub-task II. We ranked 1st in Emotion Classification sub-task and 3rd in Empathy Prediction sub-task