Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints. Adversarial training is a strong form of data augmentation that optimizes for worst-case predictions in a compact space around each data-point, resulting in neural networks that make much more robust predictions. In this paper, we bring these ideas together by adversarially probing the space between datapoints, using projected gradient descent (PGD). The fundamental approach in this work is to leverage backpropagation through the mixup interpolation during training to optimize for places where the network makes unsmooth and incongruous predictions. Additionally, we also explore several modifications and nuances, like optimization of the mixup ratio and geometrical label assignment, and discuss their impact on enhancing network robustness. Through these ideas, we have been able to train networks that robustly generalize better; experiments on CIFAR-10 and CIFAR-100 demonstrate consistent improvements in accuracy against strong adversaries, including the recent strong ensemble attack AutoAttack. Our source code would be released for reproducibility.
We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.
In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a tangible impact on performances when applied to graph data. To do so, we experiment with a structure-agnostic model and a deep graph network in a robust and controlled environment on three different datasets. The benchmark is complemented by an investigation on the effect of structure-preserving regularization techniques on catastrophic forgetting. We find that replay is the most effective strategy in so far, which also benefits the most from the use of regularization. Our findings suggest interesting future research at the intersection of the continual and graph representation learning fields. Finally, we provide researchers with a flexible software framework to reproduce our results and carry out further experiments.
With the development of medical computer-aided diagnostic systems, pulmonary artery-vein(A/V) separation plays a crucial role in assisting doctors in preoperative planning for lung cancer surgery. However, distinguishing arterial from venous irrigation in chest CT images remains a challenge due to the similarity and complex structure of the arteries and veins. We propose a novel method for automatic separation of pulmonary arteries and veins from chest CT images. The method consists of three parts. First, global connection information and local feature information are used to construct a complete topological tree and ensure the continuity of vessel reconstruction. Second, the Twin-Pipe network proposed can automatically learn the differences between arteries and veins at different levels to reduce classification errors caused by changes in terminal vessel characteristics. Finally, the topology optimizer considers interbranch and intrabranch topological relationships to maintain spatial consistency to avoid the misclassification of A/V irrigations. We validate the performance of the method on chest CT images. Compared with manual classification, the proposed method achieves an average accuracy of 96.2% on noncontrast chest CT. In addition, the method has been proven to have good generalization, that is, the accuracies of 93.8% and 94.8% are obtained for CT scans from other devices and other modes, respectively. The result of pulmonary artery-vein obtained by the proposed method can provide better assistance for preoperative planning of lung cancer surgery.
Combining multiple machine learning models into an ensemble is known to provide superior performance levels compared to the individual components forming the ensemble. This is because models can complement each other in taking better decisions. Instead of just combining the models, we propose a self-paced ensemble learning scheme in which models learn from each other over several iterations. During the self-paced learning process based on pseudo-labeling, in addition to improving the individual models, our ensemble also gains knowledge about the target domain. To demonstrate the generality of our self-paced ensemble learning (SPEL) scheme, we conduct experiments on three audio tasks. Our empirical results indicate that SPEL significantly outperforms the baseline ensemble models. We also show that applying self-paced learning on individual models is less effective, illustrating the idea that models in the ensemble actually learn from each other.
This study provides an efficient approach for using text data to calculate patent-to-patent (p2p) technological similarity, and presents a hybrid framework for leveraging the resulting p2p similarity for applications such as semantic search and automated patent classification. We create embeddings using Sentence-BERT (SBERT) based on patent claims. We leverage SBERTs efficiency in creating embedding distance measures to map p2p similarity in large sets of patent data. We deploy our framework for classification with a simple Nearest Neighbors (KNN) model that predicts Cooperative Patent Classification (CPC) of a patent based on the class assignment of the K patents with the highest p2p similarity. We thereby validate that the p2p similarity captures their technological features in terms of CPC overlap, and at the same demonstrate the usefulness of this approach for automatic patent classification based on text data. Furthermore, the presented classification framework is simple and the results easy to interpret and evaluate by end-users. In the out-of-sample model validation, we are able to perform a multi-label prediction of all assigned CPC classes on the subclass (663) level on 1,492,294 patents with an accuracy of 54% and F1 score > 66%, which suggests that our model outperforms the current state-of-the-art in text-based multi-label and multi-class patent classification. We furthermore discuss the applicability of the presented framework for semantic IP search, patent landscaping, and technology intelligence. We finally point towards a future research agenda for leveraging multi-source patent embeddings, their appropriateness across applications, as well as to improve and validate patent embeddings by creating domain-expert curated Semantic Textual Similarity (STS) benchmark datasets.
Inductive inference in supervised classification context constitutes to methods and approaches to assign some objects or items into different predefined classes using a formal rule that is derived from training data and possibly some additional auxiliary information. The optimality of such an assignment varies under different conditions due to intrinsic attributes of the objects being considered for such a task. One of these cases is when all the objects' features are discrete variables with a priori known categories. As another example, one can consider a modification of this case with a priori unknown categories. These two cases are the main focus of this thesis and based on Bayesian inductive theories, de Finetti type exchangeability is a suitable assumption that facilitates the derivation of classifiers in the former scenario. On the contrary, this type of exchangeability is not applicable in the latter case, instead, it is possible to utilise the partition exchangeability due to John Kingman. These two types of exchangeabilities are discussed and furthermore here I investigate inductive supervised classifiers based on both types of exchangeabilities. I further demonstrate that the classifiers based on de Finetti type exchangeability can optimally handle test items independently of each other in the presence of infinite amounts of training data while on the other hand, classifiers based on partition exchangeability still continue to benefit from joint labelling of all the test items. Additionally, it is shown that the inductive learning process for the simultaneous classifier saturates when the amount of test data tends to infinity.
Perhaps surprisingly sewerage infrastructure is one of the most costly infrastructures in modern society. Sewer pipes are manually inspected to determine whether the pipes are defective. However, this process is limited by the number of qualified inspectors and the time it takes to inspect a pipe. Automatization of this process is therefore of high interest. So far, the success of computer vision approaches for sewer defect classification has been limited when compared to the success in other fields mainly due to the lack of public datasets. To this end, in this work we present a large novel and publicly available multi-label classification dataset for image-based sewer defect classification called Sewer-ML. The Sewer-ML dataset consists of 1.3 million images annotated by professional sewer inspectors from three different utility companies across nine years. Together with the dataset, we also present a benchmark algorithm and a novel metric for assessing performance. The benchmark algorithm is a result of evaluating 12 state-of-the-art algorithms, six from the sewer defect classification domain and six from the multi-label classification domain, and combining the best performing algorithms. The novel metric is a class-importance weighted F2 score, $\text{F}2_{\text{CIW}}$, reflecting the economic impact of each class, used together with the normal pipe F1 score, $\text{F}1_{\text{Normal}}$. The benchmark algorithm achieves an $\text{F}2_{\text{CIW}}$ score of 55.11% and $\text{F}1_{\text{Normal}}$ score of 90.94%, leaving ample room for improvement on the Sewer-ML dataset. The code, models, and dataset are available at the project page https://vap.aau.dk/sewer-ml/
Disease classification relying solely on imaging data attracts great interest in medical image analysis. Current models could be further improved, however, by also employing Electronic Health Records (EHRs), which contain rich information on patients and findings from clinicians. It is challenging to incorporate this information into disease classification due to the high reliance on clinician input in EHRs, limiting the possibility for automated diagnosis. In this paper, we propose \textit{variational knowledge distillation} (VKD), which is a new probabilistic inference framework for disease classification based on X-rays that leverages knowledge from EHRs. Specifically, we introduce a conditional latent variable model, where we infer the latent representation of the X-ray image with the variational posterior conditioning on the associated EHR text. By doing so, the model acquires the ability to extract the visual features relevant to the disease during learning and can therefore perform more accurate classification for unseen patients at inference based solely on their X-ray scans. We demonstrate the effectiveness of our method on three public benchmark datasets with paired X-ray images and EHRs. The results show that the proposed variational knowledge distillation can consistently improve the performance of medical image classification and significantly surpasses current methods.
Hyperspectral Image(HSI) classification is the most vibrant field of research in the hyperspectral community, which aims to assign each pixel in the image to one certain category based on its spectral-spatial characteristics. Recently, some spectral-spatial-feature based DCNNs have been proposed and demonstrated remarkable classification performance. When facing a real HSI, however, these Networks have to deal with the pixels in the image one by one. The pixel-wise processing strategy is inefficient since there are numerous repeated calculations between adjacent pixels. In this paper, firstly, a brand new Network design mechanism TPPI (training based on pixel and prediction based on image) is proposed for HSI classification, which makes it possible to provide efficient and practical HSI classification with the restrictive conditions attached to the hyperspectral dataset. And then, according to the TPPI mechanism, TPPI-Net is derived based on the state of the art networks for HSI classification. Experimental results show that the proposed TPPI-Net can not only obtain high classification accuracy equivalent to the state of the art networks for HSI classification, but also greatly reduce the computational complexity of hyperspectral image prediction.
The rise of social media has led to the increasing of comments on online forums. However, there still exists invalid comments which are not informative for users. Moreover, those comments are also quite toxic and harmful to people. In this paper, we create a dataset for constructive and toxic speech detection, named UIT-ViCTSD (Vietnamese Constructive and Toxic Speech Detection dataset) with 10,000 human-annotated comments. For these tasks, we propose a system for constructive and toxic speech detection with the state-of-the-art transfer learning model in Vietnamese NLP as PhoBERT. With this system, we obtain F1-scores of 78.59% and 59.40% for classifying constructive and toxic comments, respectively. Besides, we implement various baseline models as traditional Machine Learning and Deep Neural Network-Based models to evaluate the dataset. With the results, we can solve several tasks on the online discussions and develop the framework for identifying constructiveness and toxicity of Vietnamese social media comments automatically.
Early detection of dementia through specific biomarkers in MR images plays a critical role in developing support strategies proactively. Fazekas scale facilitates an accurate quantitative assessment of the severity of white matter lesions and hence the disease. Imaging Biomarkers of dementia are multiple and comprehensive documentation of them is time-consuming. Therefore, any effort to automatically extract these biomarkers will be of clinical value while reducing inter-rater discrepancies. To tackle this problem, we propose to classify the disease severity based on the Fazekas scale through the visual biomarkers, namely the Periventricular White Matter (PVWM) and the Deep White Matter (DWM) changes, in the real-world setting of thick-slice MRI. Small training sample size and weak supervision in form of assigning severity labels to the whole MRI stack are among the main challenges. To combat the mentioned issues, we have developed a deep learning pipeline that employs self-supervised representation learning, multiple instance learning, and appropriate pre-processing steps. We use pretext tasks such as non-linear transformation, local shuffling, in- and out-painting for self-supervised learning of useful features in this domain. Furthermore, an attention model is used to determine the relevance of each MRI slice for predicting the Fazekas scale in an unsupervised manner. We show the significant superiority of our method in distinguishing different classes of dementia compared to state-of-the-art methods in our mentioned setting, which improves the macro averaged F1-score of state-of-the-art from 61% to 76% in PVWM, and from 58% to 69.2% in DWM.
Large-area crop classification using multi-spectral imagery is a widely studied problem for several decades and is generally addressed using classical Random Forest classifier. Recently, deep convolutional neural networks (DCNN) have been proposed. However, these methods only achieved results comparable with Random Forest. In this work, we present a novel CNN based architecture for large-area crop classification. Our methodology combines both spatio-temporal analysis via 3D CNN as well as temporal analysis via 1D CNN. We evaluated the efficacy of our approach on Yolo and Imperial county benchmark datasets. Our combined strategy outperforms both classical as well as recent DCNN based methods in terms of classification accuracy by 2% while maintaining a minimum number of parameters and the lowest inference time.
The new type of Coronavirus disease called COVID-19 continues to spread quite rapidly. Although it shows some specific symptoms, this disease, which can show different symptoms in almost every individual, has caused hundreds of thousands of patients to die. Although healthcare professionals work hard to prevent further loss of life, the rate of disease spread is very high. For this reason, the help of computer aided diagnosis (CAD) and artificial intelligence (AI) algorithms is vital. In this study, a method based on optimization of convolutional neural network (CNN) architecture, which is the most effective image analysis method of today, is proposed to fulfill the mentioned COVID-19 detection needs. First, COVID-19 images are trained using ResNet-50 and VGG-16 architectures. Then, features in the last layer of these two architectures are combined with feature fusion. These new image features matrices obtained with feature fusion are classified for COVID detection. A multi-layer perceptron (MLP) structure optimized by the whale optimization algorithm is used for the classification process. The obtained results show that the performance of the proposed framework is almost 4.5% higher than VGG-16 performance and almost 3.5% higher than ResNet-50 performance.
Self-supervised pre-training using so-called "pretext" tasks has recently shown impressive performance across a wide range of modalities. In this work, we advance self-supervised learning from permutations, by pre-training a model to reorder shuffled parts of the spectrogram of an audio signal, to improve downstream classification performance. We make two main contributions. First, we overcome the main challenges of integrating permutation inversions into an end-to-end training scheme, using recent advances in differentiable ranking. This was heretofore sidestepped by casting the reordering task as classification, fundamentally reducing the space of permutations that can be exploited. Our experiments validate that learning from all possible permutations improves the quality of the pre-trained representations over using a limited, fixed set. Second, we show that inverting permutations is a meaningful pretext task for learning audio representations in an unsupervised fashion. In particular, we improve instrument classification and pitch estimation of musical notes by reordering spectrogram patches in the time-frequency space.
Active learning aims to improve the performance of task model by selecting the most informative samples with a limited budget. Unlike most recent works that focused on applying active learning for image classification, we propose an effective Consistency-based Active Learning method for object Detection (CALD), which fully explores the consistency between original and augmented data. CALD has three appealing benefits. (i) CALD is systematically designed by investigating the weaknesses of existing active learning methods, which do not take the unique challenges of object detection into account. (ii) CALD unifies box regression and classification with a single metric, which is not concerned by active learning methods for classification. CALD also focuses on the most informative local region rather than the whole image, which is beneficial for object detection. (iii) CALD not only gauges individual information for sample selection, but also leverages mutual information to encourage a balanced data distribution. Extensive experiments show that CALD significantly outperforms existing state-of-the-art task-agnostic and detection-specific active learning methods on general object detection datasets. Based on the Faster R-CNN detector, CALD consistently surpasses the baseline method (random selection) by 2.9/2.8/0.8 mAP on average on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO. Code is available at \url{https://github.com/we1pingyu/CALD}
Supervised learning techniques are at the center of many tasks in remote sensing. Unfortunately, these methods, especially recent deep learning methods, often require large amounts of labeled data for training. Even though satellites acquire large amounts of data, labeling the data is often tedious, expensive and requires expert knowledge. Hence, improved methods that require fewer labeled samples are needed. We present MSMatch, the first semi-supervised learning approach competitive with supervised methods on scene classification on the EuroSAT and UC Merced Land Use benchmark datasets. We test both RGB and multispectral images of EuroSAT and perform various ablation studies to identify the critical parts of the model. The trained neural network achieves state-of-the-art results on EuroSAT with an accuracy that is up to 19.76% better than previous methods depending on the number of labeled training examples. With just five labeled examples per class, we reach 94.53% and 95.86% accuracy on the EuroSAT RGB and multispectral datasets, respectively. On the UC Merced Land Use dataset, we outperform previous works by up to 5.59% and reach 90.71% with five labeled examples. Our results show that MSMatch is capable of greatly reducing the requirements for labeled data. It translates well to multispectral data and should enable various applications that are currently infeasible due to a lack of labeled data. We provide the source code of MSMatch online to enable easy reproduction and quick adoption.
There have been various types of pretraining architectures including autoencoding models (e.g., BERT), autoregressive models (e.g., GPT), and encoder-decoder models (e.g., T5). However, none of the pretraining frameworks performs the best for all tasks of three main categories including natural language understanding (NLU), unconditional generation, and conditional generation. We propose a General Language Model (GLM) based on autoregressive blank infilling to address this challenge. GLM improves blank filling pretraining by adding 2D positional encodings and allowing an arbitrary order to predict spans, which results in performance gains over BERT and T5 on NLU tasks. Meanwhile, GLM can be pretrained for different types of tasks by varying the number and lengths of blanks. On a wide range of tasks across NLU, conditional and unconditional generation, GLM outperforms BERT, T5, and GPT given the same model sizes and data, and achieves the best performance from a single pretrained model with 1.25x parameters of BERT Large , demonstrating its generalizability to different downstream tasks.
To facilitate implementation of high-accuracy deep neural networks especially on resource-constrained devices, maintaining low computation requirements is crucial. Using very deep models for classification purposes not only decreases the neural network training speed and increases the inference time, but also need more data for higher prediction accuracy and to mitigate false positives. In this paper, we propose an efficient and lightweight deep classification ensemble structure based on a combination of simple color features, which is particularly designed for "high-accuracy" image classifications with low false positives. We designed, implemented, and evaluated our approach for explosion detection use-case applied to images and videos. Our evaluation results based on a large test test show considerable improvements on the prediction accuracy compared to the popular ResNet-50 model, while benefiting from 7.64x faster inference and lower computation cost. While we applied our approach to explosion detection, our approach is general and can be applied to other similar classification use cases as well. Given the insight gained from our experiments, we hence propose a "think small, think many" philosophy in classification scenarios: that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, lightweight models with narrowed-down color spaces can possibly lead to predictions with higher accuracy.
We introduce a novel fine-grained dataset and benchmark, the Danish Fungi 2020 (DF20). The dataset, constructed from observations submitted to the Atlas of Danish Fungi, is unique in its taxonomy-accurate class labels, small number of errors, highly unbalanced long-tailed class distribution, rich observation metadata, and well-defined class hierarchy. DF20 has zero overlap with ImageNet, allowing unbiased comparison of models fine-tuned from publicly available ImageNet checkpoints. The proposed evaluation protocol enables testing the ability to improve classification using metadata -- e.g. precise geographic location, habitat, and substrate, facilitates classifier calibration testing, and finally allows to study the impact of the device settings on the classification performance. Experiments using Convolutional Neural Networks (CNN) and the recent Vision Transformers (ViT) show that DF20 presents a challenging task. Interestingly, ViT achieves results superior to CNN baselines with 80.45% accuracy and 0.743 macro F1 score, reducing the CNN error by 9% and 12% respectively. A simple procedure for including metadata into the decision process improves the classification accuracy by more than 2.95 percentage points, reducing the error rate by 15%. The source code for all methods and experiments is available at https://sites.google.com/view/danish-fungi-dataset.