Shortage of annotated data is one of the greatest bottlenecks in biomedical image analysis. Meta learning studies how learning systems can increase in efficiency through experience and could thus evolve as an important concept to overcome data sparsity. However, the core capability of meta learning-based approaches is the identification of similar previous tasks given a new task - a challenge largely unexplored in the biomedical imaging domain. In this paper, we address the problem of quantifying task similarity with a concept that we refer to as task fingerprinting. The concept involves converting a given task, represented by imaging data and corresponding labels, to a fixed-length vector representation. In fingerprint space, different tasks can be directly compared irrespective of their data set sizes, types of labels or specific resolutions. An initial feasibility study in the field of surgical data science (SDS) with 26 classification tasks from various medical and non-medical domains suggests that task fingerprinting could be leveraged for both (1) selecting appropriate data sets for pretraining and (2) selecting appropriate architectures for a new task. Task fingerprinting could thus become an important tool for meta learning in SDS and other fields of biomedical image analysis.
COVID-19 (Coronavirus disease 2019) has been quickly spreading since its outbreak, impacting financial markets and healthcare systems globally. Countries all around the world have adopted a number of extraordinary steps to restrict the spreading virus, where early COVID-19 diagnosis is essential. Medical images such as X-ray images and Computed Tomography scans are becoming one of the main diagnostic tools to combat COVID-19 with the aid of deep learning-based systems. In this survey, we investigate the main contributions of deep learning applications using medical images in fighting against COVID-19 from the aspects of image classification, lesion localization, and severity quantification, and review different deep learning architectures and some image preprocessing techniques for achieving a preciser diagnosis. We also provide a summary of the X-ray and CT image datasets used in various studies for COVID-19 detection. The key difficulties and potential applications of deep learning in fighting against COVID-19 are finally discussed. This work summarizes the latest methods of deep learning using medical images to diagnose COVID-19, highlighting the challenges and inspiring more studies to keep utilizing the advantages of deep learning to combat COVID-19.
The deep learning technique has been shown to be effectively addressed several image analysis tasks in the computer-aided diagnosis scheme for mammography. The training of an efficacious deep learning model requires large data with diverse styles and qualities. The diversity of data often comes from the use of various scanners of vendors. But, in practice, it is impractical to collect a sufficient amount of diverse data for training. To this end, a novel contrastive learning is developed to equip the deep learning models with better style generalization capability. Specifically, the multi-style and multi-view unsupervised self-learning scheme is carried out to seek robust feature embedding against style diversity as a pretrained model. Afterward, the pretrained network is further fine-tuned to the downstream tasks, e.g., mass detection, matching, BI-RADS rating, and breast density classification. The proposed method has been evaluated extensively and rigorously with mammograms from various vendor style domains and several public datasets. The experimental results suggest that the proposed domain generalization method can effectively improve performance of four mammographic image tasks on the data from both seen and unseen domains, and outperform many state-of-the-art (SOTA) generalization methods.
Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Probabilistic Cross-Modal Embeddings (named PCME++) by introducing a new probabilistic distance with a closed-form solution. In addition, two optimization techniques are proposed to enhance PCME++ further: first, the incorporation of pseudo-positives to prevent the negative effect under massive false negatives; second, mixed sample data augmentation for probabilistic matching. Experimental results on MS-COCO Caption and two extended benchmarks, CxC and ECCV Caption, demonstrate the effectiveness of PCME++ compared to state-of-the-art ITM methods. The robustness of PCME++ is also evaluated under noisy image-text correspondences. In addition, the potential applicability of PCME++ in automatic prompt-filtering for zero-shot classification is shown. The code is available at https://github.com/naver-ai/pcmepp
Assessing the robustness of deep neural networks against out-of-distribution inputs is crucial, especially in safety-critical domains like autonomous driving, but also in safety systems where malicious actors can digitally alter inputs to circumvent safety guards. However, designing effective out-of-distribution tests that encompass all possible scenarios while preserving accurate label information is a challenging task. Existing methodologies often entail a compromise between variety and constraint levels for attacks and sometimes even both. In a first step towards a more holistic robustness evaluation of image classification models, we introduce an attack method based on image solarization that is conceptually straightforward yet avoids jeopardizing the global structure of natural images independent of the intensity. Through comprehensive evaluations of multiple ImageNet models, we demonstrate the attack's capacity to degrade accuracy significantly, provided it is not integrated into the training augmentations. Interestingly, even then, no full immunity to accuracy deterioration is achieved. In other settings, the attack can often be simplified into a black-box attack with model-independent parameters. Defenses against other corruptions do not consistently extend to be effective against our specific attack. Project website: https://github.com/paulgavrikov/adversarial_solarization
A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence. In this work, we introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i.e., few-shot), and follow instructions (i.e., zero-shot). Specifically, we train Kosmos-1 from scratch on web-scale multimodal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. We evaluate various settings, including zero-shot, few-shot, and multimodal chain-of-thought prompting, on a wide range of tasks without any gradient updates or finetuning. Experimental results show that Kosmos-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP (directly fed with document images), (ii) perception-language tasks, including multimodal dialogue, image captioning, visual question answering, and (iii) vision tasks, such as image recognition with descriptions (specifying classification via text instructions). We also show that MLLMs can benefit from cross-modal transfer, i.e., transfer knowledge from language to multimodal, and from multimodal to language. In addition, we introduce a dataset of Raven IQ test, which diagnoses the nonverbal reasoning capability of MLLMs.
Widespread outreach programs using remote retinal imaging have proven to decrease the risk from diabetic retinopathy, the leading cause of blindness in the US. However, this process still requires manual verification of image quality and grading of images for level of disease by a trained human grader and will continue to be limited by the lack of such scarce resources. Computer-aided diagnosis of retinal images have recently gained increasing attention in the machine learning community. In this paper, we introduce a set of neural networks for diabetic retinopathy classification of fundus retinal images. We evaluate the efficiency of the proposed classifiers in combination with preprocessing and augmentation steps on a sample dataset. Our experimental results show that neural networks in combination with preprocessing on the images can boost the classification accuracy on this dataset. Moreover the proposed models are scalable and can be used in large scale datasets for diabetic retinopathy detection. The models introduced in this paper can be used to facilitate the diagnosis and speed up the detection process.
Deep learning models have demonstrated high-quality performance in areas such as image classification and speech processing. However, creating a deep learning model using electronic health record (EHR) data, requires addressing particular privacy challenges that are unique to researchers in this domain. This matter focuses attention on generating realistic synthetic data while ensuring privacy. In this paper, we propose a novel framework called correlation-capturing Generative Adversarial Network (CorGAN), to generate synthetic healthcare records. In CorGAN we utilize Convolutional Neural Networks to capture the correlations between adjacent medical features in the data representation space by combining Convolutional Generative Adversarial Networks and Convolutional Autoencoders. To demonstrate the model fidelity, we show that CorGAN generates synthetic data with performance similar to that of real data in various Machine Learning settings such as classification and prediction. We also give a privacy assessment and report on statistical analysis regarding realistic characteristics of the synthetic data. The software of this work is open-source and is available at: https://github.com/astorfi/cor-gan.
We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong differential privacy (DP) guarantees with minor loss of accuracy, a similar practice yields punishing trade-offs in vision tasks. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset. AdaMix incorporates few-shot training, or cross-modal zero-shot learning, on public data prior to private fine-tuning, to improve the trade-off. AdaMix reduces the error increase from the non-private upper bound from the 167-311\% of the baseline, on average across 6 datasets, to 68-92\% depending on the desired privacy level selected by the user. AdaMix tackles the trade-off arising in visual classification, whereby the most privacy sensitive data, corresponding to isolated points in representation space, are also critical for high classification accuracy. In addition, AdaMix comes with strong theoretical privacy guarantees and convergence analysis.
The automatic early diagnosis of prodromal stages of Alzheimer's disease is of great relevance for patient treatment to improve quality of life. We address this problem as a multi-modal classification task. Multi-modal data provides richer and complementary information. However, existing techniques only consider either lower order relations between the data and single/multi-modal imaging data. In this work, we introduce a novel semi-supervised hypergraph learning framework for Alzheimer's disease diagnosis. Our framework allows for higher-order relations among multi-modal imaging and non-imaging data whilst requiring a tiny labelled set. Firstly, we introduce a dual embedding strategy for constructing a robust hypergraph that preserves the data semantics. We achieve this by enforcing perturbation invariance at the image and graph levels using a contrastive based mechanism. Secondly, we present a dynamically adjusted hypergraph diffusion model, via a semi-explicit flow, to improve the predictive uncertainty. We demonstrate, through our experiments, that our framework is able to outperform current techniques for Alzheimer's disease diagnosis.
Malware detection plays a crucial role in cyber-security with the increase in malware growth and advancements in cyber-attacks. Previously unseen malware which is not determined by security vendors are often used in these attacks and it is becoming inevitable to find a solution that can self-learn from unlabeled sample data. This paper presents SHERLOCK, a self-supervision based deep learning model to detect malware based on the Vision Transformer (ViT) architecture. SHERLOCK is a novel malware detection method which learns unique features to differentiate malware from benign programs with the use of image-based binary representation. Experimental results using 1.2 million Android applications across a hierarchy of 47 types and 696 families, shows that self-supervised learning can achieve an accuracy of 97% for the binary classification of malware which is higher than existing state-of-the-art techniques. Our proposed model is also able to outperform state-of-the-art techniques for multi-class malware classification of types and family with macro-F1 score of .497 and .491 respectively.
Masked Image Modelling (MIM) has been shown to be an efficient self-supervised learning (SSL) pre-training paradigm when paired with transformer architectures and in the presence of a large amount of unlabelled natural images. The combination of the difficulties in accessing and obtaining large amounts of labeled data and the availability of unlabelled data in the medical imaging domain makes MIM an interesting approach to advance deep learning (DL) applications based on 3D medical imaging data. Nevertheless, SSL and, in particular, MIM applications with medical imaging data are rather scarce and there is still uncertainty. around the potential of such a learning paradigm in the medical domain. We study MIM in the context of Prostate Cancer (PCa) lesion classification with T2 weighted (T2w) axial magnetic resonance imaging (MRI) data. In particular, we explore the effect of using MIM when coupled with convolutional neural networks (CNNs) under different conditions such as different masking strategies, obtaining better results in terms of AUC than other pre-training strategies like ImageNet weight initialization.
Machine Learning (ML) algorithms that perform classification may predict the wrong class, experiencing misclassifications. It is well-known that misclassifications may have cascading effects on the encompassing system, possibly resulting in critical failures. This paper proposes SPROUT, a Safety wraPper thROugh ensembles of UncertainTy measures, which suspects misclassifications by computing uncertainty measures on the inputs and outputs of a black-box classifier. If a misclassification is detected, SPROUT blocks the propagation of the output of the classifier to the encompassing system. The resulting impact on safety is that SPROUT transforms erratic outputs (misclassifications) into data omission failures, which can be easily managed at the system level. SPROUT has a broad range of applications as it fits binary and multi-class classification, comprising image and tabular datasets. We experimentally show that SPROUT always identifies a huge fraction of the misclassifications of supervised classifiers, and it is able to detect all misclassifications in specific cases. SPROUT implementation contains pre-trained wrappers, it is publicly available and ready to be deployed with minimal effort.
In this paper, we tackle Multi-Source Domain Adaptation (MSDA), a task in transfer learning where one adapts multiple heterogeneous, labeled source probability measures towards a different, unlabeled target measure. We propose a novel framework for MSDA, based on Optimal Transport (OT) and Gaussian Mixture Models (GMMs). Our framework has two key advantages. First, OT between GMMs can be solved efficiently via linear programming. Second, it provides a convenient model for supervised learning, especially classification, as components in the GMM can be associated with existing classes. Based on the GMM-OT problem, we propose a novel technique for calculating barycenters of GMMs. Based on this novel algorithm, we propose two new strategies for MSDA: GMM-Wasserstein Barycenter Transport (WBT) and GMM-Dataset Dictionary Learning (DaDiL). We empirically evaluate our proposed methods on four benchmarks in image classification and fault diagnosis, showing that we improve over the prior art while being faster and involving fewer parameters. Our code is publicly available at https://github.com/eddardd/gmm_msda
In nations such as Bangladesh, agriculture plays a vital role in providing livelihoods for a significant portion of the population. Identifying and classifying plant diseases early is critical to prevent their spread and minimize their impact on crop yield and quality. Various computer vision techniques can be used for such detection and classification. While CNNs have been dominant on such image classification tasks, vision transformers has become equally good in recent time also. In this paper we study the various computer vision techniques for Bangladeshi rice leaf disease detection. We use the Dhan-Shomadhan -- a Bangladeshi rice leaf disease dataset, to experiment with various CNN and ViT models. We also compared the performance of such deep neural network architecture with traditional machine learning architecture like Support Vector Machine(SVM). We leveraged transfer learning for better generalization with lower amount of training data. Among the models tested, ResNet50 exhibited the best performance over other CNN and transformer-based models making it the optimal choice for this task.
As an unsupervised dimensionality reduction method, principal component analysis (PCA) has been widely considered as an efficient and effective preprocessing step for hyperspectral image (HSI) processing and analysis tasks. It takes each band as a whole and globally extracts the most representative bands. However, different homogeneous regions correspond to different objects, whose spectral features are diverse. It is obviously inappropriate to carry out dimensionality reduction through a unified projection for an entire HSI. In this paper, a simple but very effective superpixelwise PCA approach, called SuperPCA, is proposed to learn the intrinsic low-dimensional features of HSIs. In contrast to classical PCA models, SuperPCA has four main properties. (1) Unlike the traditional PCA method based on a whole image, SuperPCA takes into account the diversity in different homogeneous regions, that is, different regions should have different projections. (2) Most of the conventional feature extraction models cannot directly use the spatial information of HSIs, while SuperPCA is able to incorporate the spatial context information into the unsupervised dimensionality reduction by superpixel segmentation. (3) Since the regions obtained by superpixel segmentation have homogeneity, SuperPCA can extract potential low-dimensional features even under noise. (4) Although SuperPCA is an unsupervised method, it can achieve competitive performance when compared with supervised approaches. The resulting features are discriminative, compact, and noise resistant, leading to improved HSI classification performance. Experiments on three public datasets demonstrate that the SuperPCA model significantly outperforms the conventional PCA based dimensionality reduction baselines for HSI classification. The Matlab source code is available at https://github.com/junjun-jiang/SuperPCA
Recently, by using deep neural network based algorithms, object classification, detection and semantic segmentation solutions are significantly improved. However, one challenge for 2D image-based systems is that they cannot provide accurate 3D location information. This is critical for location sensitive applications such as autonomous driving and robot navigation. On the other hand, 3D methods, such as RGB-D and RGB-LiDAR based systems, can provide solutions that significantly improve the RGB only approaches. That is why this is an interesting research area for both industry and academia. Compared with 2D image-based systems, 3D-based systems are more complicated due to the following five reasons: 1) Data representation itself is more complicated. 3D images can be represented by point clouds, meshes, volumes. 2D images have pixel grid representations. 2) The computation and memory resource requirement is higher as an extra dimension is added. 3) Different distribution of the objects and difference in scene areas between indoor and outdoor make one unified framework hard to achieve. 4) 3D data, especially for the outdoor scenario, is sparse compared with the dense 2D images which makes the detection task more challenging. Finally, large size labelled datasets, which are extremely important for supervised based algorithms, are still under construction compared with well-built 2D datasets such as ImageNet. Based on challenges listed above, the described systems are organized by application scenarios, data representation methods and main tasks addressed. At the same time, critical 2D based systems which greatly influence the 3D ones are also introduced to show the connection between them.
As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it hard to identify the most promising ideas in training robust models. A key challenge in benchmarking robustness is that its evaluation is often error-prone leading to robustness overestimation. Our goal is to establish a standardized benchmark of adversarial robustness, which as accurately as possible reflects the robustness of the considered models within a reasonable computational budget. To this end, we start by considering the image classification task and introduce restrictions (possibly loosened in the future) on the allowed models. We evaluate adversarial robustness with AutoAttack, an ensemble of white- and black-box attacks, which was recently shown in a large-scale study to improve almost all robustness evaluations compared to the original publications. To prevent overadaptation of new defenses to AutoAttack, we welcome external evaluations based on adaptive attacks, especially where AutoAttack flags a potential overestimation of robustness. Our leaderboard, hosted at https://robustbench.github.io/, contains evaluations of 120+ models and aims at reflecting the current state of the art in image classification on a set of well-defined tasks in $\ell_\infty$- and $\ell_2$-threat models and on common corruptions, with possible extensions in the future. Additionally, we open-source the library https://github.com/RobustBench/robustbench that provides unified access to 80+ robust models to facilitate their downstream applications. Finally, based on the collected models, we analyze the impact of robustness on the performance on distribution shifts, calibration, out-of-distribution detection, fairness, privacy leakage, smoothness, and transferability.
While 2D object detection has improved significantly over the past, real world applications of computer vision often require an understanding of the 3D layout of a scene. Many recent approaches to 3D detection use LiDAR point clouds for prediction. We propose a method that only uses a single RGB image, thus enabling applications in devices or vehicles that do not have LiDAR sensors. By using an RGB image, we can leverage the maturity and success of recent 2D object detectors, by extending a 2D detector with a 3D detection head. In this paper we discuss different approaches and experiments, including both regression and classification methods, for designing this 3D detection head. Furthermore, we evaluate how subproblems and implementation details impact the overall prediction result. We use the KITTI dataset for training, which consists of street traffic scenes with class labels, 2D bounding boxes and 3D annotations with seven degrees of freedom. Our final architecture is based on Faster R-CNN. The outputs of the convolutional backbone are fixed sized feature maps for every region of interest. Fully connected layers within the network head then propose an object class and perform 2D bounding box regression. We extend the network head by a 3D detection head, which predicts every degree of freedom of a 3D bounding box via classification. We achieve a mean average precision of 47.3% for moderately difficult data, measured at a 3D intersection over union threshold of 70%, as required by the official KITTI benchmark; outperforming previous state-of-the-art single RGB only methods by a large margin.
The current standard for a variety of computer vision tasks using smaller numbers of labelled training examples is to fine-tune from weights pre-trained on a large image classification dataset such as ImageNet. The application of transfer learning and transfer learning methods tends to be rigidly binary. A model is either pre-trained or not pre-trained. Pre-training a model either increases performance or decreases it, the latter being defined as negative transfer. Application of L2-SP regularisation that decays the weights towards their pre-trained values is either applied or all weights are decayed towards 0. This paper re-examines these assumptions. Our recommendations are based on extensive empirical evaluation that demonstrate the application of a non-binary approach to achieve optimal results. (1) Achieving best performance on each individual dataset requires careful adjustment of various transfer learning hyperparameters not usually considered, including number of layers to transfer, different learning rates for different layers and different combinations of L2SP and L2 regularization. (2) Best practice can be achieved using a number of measures of how well the pre-trained weights fit the target dataset to guide optimal hyperparameters. We present methods for non-binary transfer learning including combining L2SP and L2 regularization and performing non-traditional fine-tuning hyperparameter searches. Finally we suggest heuristics for determining the optimal transfer learning hyperparameters. The benefits of using a non-binary approach are supported by final results that come close to or exceed state of the art performance on a variety of tasks that have traditionally been more difficult for transfer learning.