Multiple Instance Learning (MIL) is widely used in analyzing histopathological Whole Slide Images (WSIs). However, existing MIL methods do not explicitly model the data distribution, and instead they only learn a bag-level or instance-level decision boundary discriminatively by training a classifier. In this paper, we propose DGMIL: a feature distribution guided deep MIL framework for WSI classification and positive patch localization. Instead of designing complex discriminative network architectures, we reveal that the inherent feature distribution of histopathological image data can serve as a very effective guide for instance classification. We propose a cluster-conditioned feature distribution modeling method and a pseudo label-based iterative feature space refinement strategy so that in the final feature space the positive and negative instances can be easily separated. Experiments on the CAMELYON16 dataset and the TCGA Lung Cancer dataset show that our method achieves new SOTA for both global classification and positive patch localization tasks.
Text Generation Models (TGMs) succeed in creating text that matches human language style reasonably well. Detectors that can distinguish between TGM-generated text and human-written ones play an important role in preventing abuse of TGM. In this paper, we describe our pipeline for the two DIALOG-22 RuATD tasks: detecting generated text (binary task) and classification of which model was used to generate text (multiclass task). We achieved 1st place on the binary classification task with an accuracy score of 0.82995 on the private test set and 4th place on the multiclass classification task with an accuracy score of 0.62856 on the private test set. We proposed an ensemble method of different pre-trained models based on the attention mechanism.
Internet traffic classification is widely used to facilitate network management. It plays a crucial role in Quality of Services (QoS), Quality of Experience (QoE), network visibility, intrusion detection, and traffic trend analyses. While there is no theoretical guarantee that deep learning (DL)-based solutions perform better than classic machine learning (ML)-based ones, DL-based models have become the common default. This paper compares well-known DL-based and ML-based models and shows that in the case of malicious traffic classification, state-of-the-art DL-based solutions do not necessarily outperform the classical ML-based ones. We exemplify this finding using two well-known datasets for a varied set of tasks, such as: malware detection, malware family classification, detection of zero-day attacks, and classification of an iteratively growing dataset. Note that, it is not feasible to evaluate all possible models to make a concrete statement, thus, the above finding is not a recommendation to avoid DL-based models, but rather empirical proof that in some cases, there are more simplistic solutions, that may perform even better.
Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as a defense for video classification has not been thoroughly studied. Our first contribution is to show that generating optimal attacks for video requires carefully tuning the attack parameters, especially the step size. Notably, we show that the optimal step size varies linearly with the attack budget. Our second contribution is to show that using a smaller (sub-optimal) attack budget at training time leads to a more robust performance at test time. Based on these findings, we propose three defenses against attacks with variable attack budgets. The first one, Adaptive AT, is a technique where the attack budget is drawn from a distribution that is adapted as training iterations proceed. The second, Curriculum AT, is a technique where the attack budget is increased as training iterations proceed. The third, Generative AT, further couples AT with a denoising generative adversarial network to boost robust performance. Experiments on the UCF101 dataset demonstrate that the proposed methods improve adversarial robustness against multiple attack types.
Learning the distribution of a continuous or categorical response variable $\boldsymbol y$ given its covariates $\boldsymbol x$ is a fundamental problem in statistics and machine learning. Deep neural network-based supervised learning algorithms have made great progress in predicting the mean of $\boldsymbol y$ given $\boldsymbol x$, but they are often criticized for their ability to accurately capture the uncertainty of their predictions. In this paper, we introduce classification and regression diffusion (CARD) models, which combine a denoising diffusion-based conditional generative model and a pre-trained conditional mean estimator, to accurately predict the distribution of $\boldsymbol y$ given $\boldsymbol x$. We demonstrate the outstanding ability of CARD in conditional distribution prediction with both toy examples and real-world datasets, the experimental results on which show that CARD in general outperforms state-of-the-art methods, including Bayesian neural network-based ones that are designed for uncertainty estimation, especially when the conditional distribution of $\boldsymbol y$ given $\boldsymbol x$ is multi-modal. In addition, we utilize the stochastic nature of the generative model outputs to obtain a finer granularity in model confidence assessment at the instance level for classification tasks.
Node classification is a fundamental graph-based task that aims to predict the classes of unlabeled nodes, for which Graph Neural Networks (GNNs) are the state-of-the-art methods. Current GNNs assume that nodes in the training set contribute equally during training. However, the quality of training nodes varies greatly, and the performance of GNNs could be harmed by two types of low-quality training nodes: (1) inter-class nodes situated near class boundaries that lack the typical characteristics of their corresponding classes. Because GNNs are data-driven approaches, training on these nodes could degrade the accuracy. (2) mislabeled nodes. In real-world graphs, nodes are often mislabeled, which can significantly degrade the robustness of GNNs. To mitigate the detrimental effect of the low-quality training nodes, we present CLNode, which employs a selective training strategy to train GNN based on the quality of nodes. Specifically, we first design a multi-perspective difficulty measurer to accurately measure the quality of training nodes. Then, based on the measured qualities, we employ a training scheduler that selects appropriate training nodes to train GNN in each epoch. To evaluate the effectiveness of CLNode, we conduct extensive experiments by incorporating it in six representative backbone GNNs. Experimental results on real-world networks demonstrate that CLNode is a general framework that can be combined with various GNNs to improve their accuracy and robustness.
Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a significant challenge for applications where the set of classes differs significantly between training and test time. In this paper, we take a closer look at the implications in the context of $\textit{few-shot learning}$. Splitting the input samples into patches and encoding these via the help of Vision Transformers allows us to establish semantic correspondences between local regions across images and independent of their respective class. The most informative patch embeddings for the task at hand are then determined as a function of the support set via online optimization at inference time, additionally providing visual interpretability of `$\textit{what matters most}$' in the image. We build on recent advances in unsupervised training of networks via masked image modelling to overcome the lack of fine-grained labels and learn the more general statistical structure of the data while avoiding negative image-level annotation influence, $\textit{aka}$ supervision collapse. Experimental results show the competitiveness of our approach, achieving new state-of-the-art results on four popular few-shot classification benchmarks for $5$-shot and $1$-shot scenarios.
Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We propose a generalization of entropy called {\em structured entropy} which uses a random partition to incorporate the structure of the target variable in a manner which retains many theoretical properties of standard entropy. We show that a structured cross-entropy loss yields better results on several classification problems where the target variable has an a priori known structure. The approach is simple, flexible, easily computable, and does not rely on a hierarchically defined notion of structure.
It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. This assumption has led to a growing body of work aiming to align deep models' decision-making processes with the fundamental properties of human vision. The reliance on shape features is primarily expected to improve the robustness of these models under covariate shift. In this paper, we revisit the significance of shape-biases for the classification of skin lesion images. Our analysis shows that different skin lesion datasets exhibit varying biases towards individual image features. Interestingly, despite deep feature extractors being inclined towards learning entangled features for skin lesion classification, individual features can still be decoded from this entangled representation. This indicates that these features are still represented in the learnt embedding spaces of the models, but not used for classification. In addition, the spectral analysis of different datasets shows that in contrast to common visual recognition, dermoscopic skin lesion classification, by nature, is reliant on complex feature combinations beyond shape-bias. As a natural consequence, shifting away from the prevalent desire of shape-biasing models can even improve skin lesion classifiers in some cases.
To assist in the development of machine learning methods for automated classification of spectroscopic data, we have generated a universal synthetic dataset that can be used for model validation. This dataset contains artificial spectra designed to represent experimental measurements from techniques including X-ray diffraction, nuclear magnetic resonance, and Raman spectroscopy. The dataset generation process features customizable parameters, such as scan length and peak count, which can be adjusted to fit the problem at hand. As an initial benchmark, we simulated a dataset containing 35,000 spectra based on 500 unique classes. To automate the classification of this data, eight different machine learning architectures were evaluated. From the results, we shed light on which factors are most critical to achieve optimal performance for the classification task. The scripts used to generate synthetic spectra, as well as our benchmark dataset and evaluation routines, are made publicly available to aid in the development of improved machine learning models for spectroscopic analysis.
Deep learning models have shown their potential for several applications. However, most of the models are opaque and difficult to trust due to their complex reasoning - commonly known as the black-box problem. Some fields, such as medicine, require a high degree of transparency to accept and adopt such technologies. Consequently, creating explainable/interpretable models or applying post-hoc methods on classifiers to build trust in deep learning models are required. Moreover, deep learning methods can be used for segmentation tasks, which typically require hard-to-obtain, time-consuming manually-annotated segmentation labels for training. This paper introduces three inherently-explainable classifiers to tackle both of these problems as one. The localisation heatmaps provided by the networks -- representing the models' focus areas and being used in classification decision-making -- can be directly interpreted, without requiring any post-hoc methods to derive information for model explanation. The models are trained by using the input image and only the classification labels as ground-truth in a supervised fashion - without using any information about the location of the region of interest (i.e. the segmentation labels), making the segmentation training of the models weakly-supervised through classification labels. The final segmentation is obtained by thresholding these heatmaps. The models were employed for the task of multi-class brain tumour classification using two different datasets, resulting in the best F1-score of 0.93 for the supervised classification task while securing a median Dice score of 0.67$\pm$0.08 for the weakly-supervised segmentation task. Furthermore, the obtained accuracy on a subset of tumour-only images outperformed the state-of-the-art glioma tumour grading binary classifiers with the best model achieving 98.7\% accuracy.
Decision trees are powerful tools for classification and regression that attract many researchers working in the burgeoning area of machine learning. One advantage of decision trees over other methods is their interpretability, which is often preferred over other higher accuracy methods that are relatively uninterpretable. A binary classification tree has two types of vertices: (i) branching vertices which have exactly two children and where datapoints are assessed on a set of discrete features; and (ii) leaf vertices at which datapoints are given a discrete prediction. An optimal binary classification tree can be obtained by solving a biobjective optimization problem that seeks to (i) maximize the number of correctly classified datapoints and (ii) minimize the number of branching vertices. In this paper, we propose four mixed integer linear optimization (MILO) formulations for designing optimal binary classification trees: two flow-based formulations and two-cut based formulations. We provide theoretical comparisons between our proposed formulations and the strongest flow-based MILO formulation of Aghaei et al. (2021). We conduct experiments on 13 publicly available datasets to show the models' ability to scale and the strength of a biobjective approach using Pareto frontiers. Our code and data are available on GitHub.
Recent advances in deep learning and computer vision have reduced many barriers to automated medical image analysis, allowing algorithms to process label-free images and improve performance. However, existing techniques have extreme computational requirements and drop a lot of performance with a reduction in batch size or training epochs. This paper presents Cross Architectural - Self Supervision (CASS), a novel self-supervised learning approach that leverages Transformer and CNN simultaneously. Compared to the existing state of the art self-supervised learning approaches, we empirically show that CASS-trained CNNs and Transformers across four diverse datasets gained an average of 3.8% with 1% labeled data, 5.9% with 10% labeled data, and 10.13% with 100% labeled data while taking 69% less time. We also show that CASS is much more robust to changes in batch size and training epochs. Notably, one of the test datasets comprised histopathology slides of an autoimmune disease, a condition with minimal data that has been underrepresented in medical imaging. The code is open source and is available on GitHub.
Texture-based classification solutions have proven their significance in many domains, from industrial inspections to health-related applications. New methods have been developed based on texture feature learning and CNN-based architectures to address computer vision use cases for images with rich texture-based features. In recent years, architectures solving texture-based classification problems and demonstrating state-of-the-art results have emerged. Yet, one limitation of these approaches is that they cannot claim to be suitable for all types of image texture patterns. Each technique has an advantage for a specific texture type only. To address this shortcoming, we propose a framework that combines more than one texture-based techniques together, uniquely, with a CNN backbone to extract the most relevant texture features. This enables the model to be trained in a self-selective manner and produce improved results over current published benchmarks -- with almost same number of model parameters. Our proposed framework works well on most texture types simultaneously and allows flexibility for additional texture-based methods to be accommodated to achieve better results than existing architectures. In this work, firstly, we present an analysis on the relative importance of existing techniques when used alone and in combination with other TE methods on benchmark datasets. Secondly, we show that Global Average Pooling which represents the spatial information -- is of less significance in comparison to the TE method(s) applied in the network while training for texture-based classification tasks. Finally, we present state-of-the-art results for several texture-based benchmark datasets by combining three existing texture-based techniques using our proposed framework.
The theoretical analysis of multi-class classification has proved that the existing multi-class classification methods can train a classifier with high classification accuracy on the test set, when the instances are precise in the training and test sets with same distribution and enough instances can be collected in the training set. However, one limitation with multi-class classification has not been solved: how to improve the classification accuracy of multi-class classification problems when only imprecise observations are available. Hence, in this paper, we propose a novel framework to address a new realistic problem called multi-class classification with imprecise observations (MCIMO), where we need to train a classifier with fuzzy-feature observations. Firstly, we give the theoretical analysis of the MCIMO problem based on fuzzy Rademacher complexity. Then, two practical algorithms based on support vector machine and neural networks are constructed to solve the proposed new problem. Experiments on both synthetic and real-world datasets verify the rationality of our theoretical analysis and the efficacy of the proposed algorithms.
Weakly supervised multi-label classification (WSML) task, which is to learn a multi-label classification using partially observed labels per image, is becoming increasingly important due to its huge annotation cost. In this work, we first regard unobserved labels as negative labels, casting the WSML task into noisy multi-label classification. From this point of view, we empirically observe that memorization effect, which was first discovered in a noisy multi-class setting, also occurs in a multi-label setting. That is, the model first learns the representation of clean labels, and then starts memorizing noisy labels. Based on this finding, we propose novel methods for WSML which reject or correct the large loss samples to prevent model from memorizing the noisy label. Without heavy and complex components, our proposed methods outperform previous state-of-the-art WSML methods on several partial label settings including Pascal VOC 2012, MS COCO, NUSWIDE, CUB, and OpenImages V3 datasets. Various analysis also show that our methodology actually works well, validating that treating large loss properly matters in a weakly supervised multi-label classification. Our code is available at https://github.com/snucml/LargeLossMatters.
Many modern deep-learning techniques do not work without enormous datasets. At the same time, several fields demand methods working in scarcity of data. This problem is even more complex when the samples have varying structures, as in the case of graphs. Graph representation learning techniques have recently proven successful in a variety of domains. Nevertheless, the employed architectures perform miserably when faced with data scarcity. On the other hand, few-shot learning allows employing modern deep learning models in scarce data regimes without waiving their effectiveness. In this work, we tackle the problem of few-shot graph classification, showing that equipping a simple distance metric learning baseline with a state-of-the-art graph embedder allows to obtain competitive results on the task. While the simplicity of the architecture is enough to outperform more complex ones, it also allows straightforward additions. To this end, we show that additional improvements may be obtained by encouraging a task-conditioned embedding space. Finally, we propose a MixUp-based online data augmentation technique acting in the latent space and show its effectiveness on the task.
Existing works often focus on reducing the architecture redundancy for accelerating image classification but ignore the spatial redundancy of the input image. This paper proposes an efficient image classification pipeline to solve this problem. We first pinpoint task-aware regions over the input image by a lightweight patch proposal network called AnchorNet. We then feed these localized semantic patches with much smaller spatial redundancy into a general classification network. Unlike the popular design of deep CNN, we aim to carefully design the Receptive Field of AnchorNet without intermediate convolutional paddings. This ensures the exact mapping from a high-level spatial location to the specific input image patch. The contribution of each patch is interpretable. Moreover, AnchorNet is compatible with any downstream architecture. Experimental results on ImageNet show that our method outperforms SOTA dynamic inference methods with fewer inference costs. Our code is available at https://github.com/winycg/AnchorNet.
Heart Disease has become one of the most serious diseases that has a significant impact on human life. It has emerged as one of the leading causes of mortality among the people across the globe during the last decade. In order to prevent patients from further damage, an accurate diagnosis of heart disease on time is an essential factor. Recently we have seen the usage of non-invasive medical procedures, such as artificial intelligence-based techniques in the field of medical. Specially machine learning employs several algorithms and techniques that are widely used and are highly useful in accurately diagnosing the heart disease with less amount of time. However, the prediction of heart disease is not an easy task. The increasing size of medical datasets has made it a complicated task for practitioners to understand the complex feature relations and make disease predictions. Accordingly, the aim of this research is to identify the most important risk-factors from a highly dimensional dataset which helps in the accurate classification of heart disease with less complications. For a broader analysis, we have used two heart disease datasets with various medical features. The classification results of the benchmarked models proved that there is a high impact of relevant features on the classification accuracy. Even with a reduced number of features, the performance of the classification models improved significantly with a reduced training time as compared with models trained on full feature set.
This article describes Jigsaw, a convolutional neural network (CNN) used in geosciences and based on Inception but tailored for geoscientific analyses. Introduces JigsawHSI (based on Jigsaw) and uses it on the land-use land-cover (LULC) classification problem with the Indian Pines, Pavia University and Salinas hyperspectral image data sets. The network is compared against HybridSN, a spectral-spatial 3D-CNN followed by 2D-CNN that achieves state-of-the-art results on the datasets. This short article proves that JigsawHSI is able to meet or exceed HybridSN's performance in all three cases. It also introduces a generalized Jigsaw architecture in d-dimensional space for any number of multimodal inputs. Additionally, the use of jigsaw in geosciences is highlighted, while the code and toolkit are made available.