This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per category, while the target domain data are unlabelled. To address the FS-UDA setting, we develop a general UDA model to solve the following two key issues: the few-shot labeled data per category and the domain adaptation between support and query sets. Our model is general in that once trained it will be able to be applied to various FS-UDA tasks from the same source and target domains. Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation. By proposing a novel concept called similarity patterns (SPs), our model not only effectively considers the spatial relationship of LDs that was ignored in previous FSL methods, but also makes the learned image similarity better serve the required domain alignment. Specifically, we propose a novel IMage-to-class sparse Similarity Encoding (IMSE) method. It learns SPs to extract the local discriminative information for classification and meanwhile aligns the covariance matrix of the SPs for domain adaptation. Also, domain adversarial training and multi-scale local feature matching are performed upon LDs. Extensive experiments conducted on a multi-domain benchmark dataset DomainNet demonstrates the state-of-the-art performance of our IMSE for the novel setting of FS-UDA. In addition, for FSL, our IMSE can also show better performance than most of recent FSL methods on miniImageNet.
Agriculture is vital for human survival and remains a major driver of several economies around the world; more so in underdeveloped and developing economies. With increasing demand for food and cash crops, due to a growing global population and the challenges posed by climate change, there is a pressing need to increase farm outputs while incurring minimal costs. Previous machine vision technologies developed for selective weeding have faced the challenge of reliable and accurate weed detection. We present approaches for plant seedlings classification with a dataset that contains 4,275 images of approximately 960 unique plants belonging to 12 species at several growth stages. We compare the performances of two traditional algorithms and a Convolutional Neural Network (CNN), a deep learning technique widely applied to image recognition, for this task. Our findings show that CNN-driven seedling classification applications when used in farming automation has the potential to optimize crop yield and improve productivity and efficiency when designed appropriately.
Supervised deep learning algorithms have enabled significant performance gains in medical image classification tasks. But these methods rely on large labeled datasets that require resource-intensive expert annotation. Semi-supervised generative adversarial network (GAN) approaches offer a means to learn from limited labeled data alongside larger unlabeled datasets, but have not been applied to discern fine-scale, sparse or localized features that define medical abnormalities. To overcome these limitations, we propose a patch-based semi-supervised learning approach and evaluate performance on classification of diabetic retinopathy from funduscopic images. Our semi-supervised approach achieves high AUC with just 10-20 labeled training images, and outperforms the supervised baselines by upto 15% when less than 30% of the training dataset is labeled. Further, our method implicitly enables interpretation of the SSL predictions. As this approach enables good accuracy, resolution and interpretability with lower annotation burden, it sets the pathway for scalable applications of deep learning in clinical imaging.
Image hash codes are produced by binarizing the embeddings of convolutional neural networks (CNN) trained for either classification or retrieval. While proxy embeddings achieve good performance on both tasks, they are non-trivial to binarize, due to a rotational ambiguity that encourages non-binary embeddings. The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity, and a procedure to design proxy sets that are nearly optimal for both classification and hashing is introduced. The resulting hash-consistent large margin (HCLM) proxies are shown to encourage saturation of hashing units, thus guaranteeing a small binarization error, while producing highly discriminative hash-codes. A semantic extension (sHCLM), aimed to improve hashing performance in a transfer scenario, is also proposed. Extensive experiments show that sHCLM embeddings achieve significant improvements over state-of-the-art hashing procedures on several small and large datasets, both within and beyond the set of training classes.
Despite deep learning (DL) success in classification problems, DL classifiers do not provide a sound mechanism to decide when to refrain from predicting. Recent works tried to control the overall prediction risk with classification with rejection options. However, existing works overlook the different significance of different classes. We introduce Set-classifier with Class-specific RIsk Bounds (SCRIB) to tackle this problem, assigning multiple labels to each example. Given the output of a black-box model on the validation set, SCRIB constructs a set-classifier that controls the class-specific prediction risks with a theoretical guarantee. The key idea is to reject when the set classifier returns more than one label. We validated SCRIB on several medical applications, including sleep staging on electroencephalogram (EEG) data, X-ray COVID image classification, and atrial fibrillation detection based on electrocardiogram (ECG) data. SCRIB obtained desirable class-specific risks, which are 35\%-88\% closer to the target risks than baseline methods.
Computer Tomography (CT) images have become quite important to diagnose diseases. CT scan slice contains a vast amount of data that may not be properly examined with the requisite precision and speed using normal visual inspection. A computer-assisted skull fracture classification expert system is needed to assist physicians. Convolutional Neural Networks (CNNs) are the most extensively used deep learning models for image categorization since most often time they outperform other models in terms of accuracy and results. The CNN models were then developed and tested, and several convolutional neural network (CNN) architectures were compared. ResNet50, which was used for feature extraction combined with a gradient boosted decision tree machine learning algorithm to act as a classifier for the categorization of skull fractures from brain CT scans into three fracture categories, had the best overall F1-score of 96%, Hamming Score of 95%, Balanced accuracy Score of 94% & ROC AUC curve of 96% for the classification of skull fractures.
Skin cancer is a global health concern, necessitating early and accurate diagnosis for improved patient outcomes. This study introduces a groundbreaking approach to skin cancer classification, employing the Vision Transformer, a state-of-the-art deep learning architecture renowned for its success in diverse image analysis tasks. Utilizing the HAM10000 dataset of 10,015 meticulously annotated skin lesion images, the model undergoes preprocessing for enhanced robustness. The Vision Transformer, adapted to the skin cancer classification task, leverages the self-attention mechanism to capture intricate spatial dependencies, achieving superior performance over traditional deep learning architectures. Segment Anything Model aids in precise segmentation of cancerous areas, attaining high IOU and Dice Coefficient. Extensive experiments highlight the model's supremacy, particularly the Google-based ViT patch-32 variant, which achieves 96.15% accuracy and showcases potential as an effective tool for dermatologists in skin cancer diagnosis, contributing to advancements in dermatological practices.
Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, but how and where are questions that remain largely unanswered. Given a multi-layered neural model, where does memorisation occur in the millions of parameters? Related work reports conflicting findings: a dominant hypothesis based on image classification is that lower layers learn generalisable features and that deeper layers specialise and memorise. Work from NLP suggests this does not apply to language models, but has been mainly focused on memorisation of facts. We expand the scope of the localisation question to 12 natural language classification tasks and apply 4 memorisation localisation techniques. Our results indicate that memorisation is a gradual process rather than a localised one, establish that memorisation is task-dependent, and give nuance to the generalisation first, memorisation second hypothesis.
Image hash algorithms generate compact binary representations that can be quickly matched by Hamming distance, thus become an efficient solution for large-scale image retrieval. This paper proposes RV-SSDH, a deep image hash algorithm that incorporates the classical VLAD (vector of locally aggregated descriptors) architecture into neural networks. Specifically, a novel neural network component is formed by coupling a random VLAD layer with a latent hash layer through a transform layer. This component can be combined with convolutional layers to realize a hash algorithm. We implement RV-SSDH as a point-wise algorithm that can be efficiently trained by minimizing classification error and quantization loss. Comprehensive experiments show this new architecture significantly outperforms baselines such as NetVLAD and SSDH, and offers a cost-effective trade-off in the state-of-the-art. In addition, the proposed random VLAD layer leads to satisfactory accuracy with low complexity, thus shows promising potentials as an alternative to NetVLAD.
The characterization and analysis of microstructure is the foundation of microstructural science, connecting the materials structure to its composition, process history, and properties. Microstructural quantification traditionally involves a human deciding a priori what to measure and then devising a purpose-built method for doing so. However, recent advances in data science, including computer vision (CV) and machine learning (ML) offer new approaches to extracting information from microstructural images. This overview surveys CV approaches to numerically encode the visual information contained in a microstructural image, which then provides input to supervised or unsupervised ML algorithms that find associations and trends in the high-dimensional image representation. CV/ML systems for microstructural characterization and analysis span the taxonomy of image analysis tasks, including image classification, semantic segmentation, object detection, and instance segmentation. These tools enable new approaches to microstructural analysis, including the development of new, rich visual metrics and the discovery of processing-microstructure-property relationships.
In imaging inverse problems, one seeks to recover an image from missing/corrupted measurements. Because such problems are ill-posed, there is great motivation to quantify the uncertainty induced by the measurement-and-recovery process. Motivated by applications where the recovered image is used for a downstream task, such as soft-output classification, we propose a task-centered approach to uncertainty quantification. In particular, we use conformal prediction to construct an interval that is guaranteed to contain the task output from the true image up to a user-specified probability, and we use the width of that interval to quantify the uncertainty contributed by measurement-and-recovery. For posterior-sampling-based image recovery, we construct locally adaptive prediction intervals. Furthermore, we propose to collect measurements over multiple rounds, stopping as soon as the task uncertainty falls below an acceptable level. We demonstrate our methodology on accelerated magnetic resonance imaging (MRI): https://github.com/jwen307/TaskUQ.
Lymphoma subtype classification has a direct impact on treatment and outcomes, necessitating models that are both accurate and explainable. This study proposes a novel explainable Multi-Instance Learning (MIL) framework that identifies subtype-specific Regions of Interest (ROIs) from Whole Slide Images (WSIs) while integrating features of cell distribution and image. Our framework simultaneously addresses three objectives: (1) indicating appropriate ROIs for each subtype, (2) explaining the frequency and spatial distribution of characteristic cell types, and (3) reaching accurate subtyping using both cell distribution and image modalities. Our method fuses cell graph and image features extracted for each patch in a WSI by a Mixture-of-Experts-based approach and classifies subtypes within an MIL framework. Experiments on a dataset of 1,233 WSIs demonstrate that our approach achieves state-of-the-art accuracy compared to ten other methods and provides region- and cell-level explanations that align with a pathologist's perspective.
We benchmark foundation models image embeddings for classification and retrieval in e-Commerce, evaluating their suitability for real-world applications. Our study spans embeddings from pre-trained convolutional and transformer models trained via supervised, self-supervised, and text-image contrastive learning. We assess full fine-tuning and transfer learning (top-tuning) on six diverse e-Commerce datasets: fashion, consumer goods, cars, food, and retail. Results show full fine-tuning consistently performs well, while text-image and self-supervised embeddings can match its performance with less training. While supervised embeddings remain stable across architectures, SSL and contrastive embeddings vary significantly, often benefiting from top-tuning. Top-tuning emerges as an efficient alternative to full fine-tuning, reducing computational costs. We also explore cross-tuning, noting its impact depends on dataset characteristics. Our findings offer practical guidelines for embedding selection and fine-tuning strategies, balancing efficiency and performance.
Electrocardiograms (ECGs), a medical monitoring technology recording cardiac activity, are widely used for diagnosing cardiac arrhythmia. The diagnosis is based on the analysis of the deformation of the signal shapes due to irregular heart rates associated with heart diseases. Due to the infeasibility of manual examination of large volumes of ECG data, this paper aims to propose an automated AI based system for ECG-based arrhythmia classification. To this front, a deep learning based solution has been proposed for ECG-based arrhythmia classification. Twelve lead electrocardiograms (ECG) of length 10 sec from 45, 152 individuals from Shaoxing People's Hospital (SPH) dataset from PhysioNet with four different types of arrhythmias were used. The sampling frequency utilized was 500 Hz. Median filtering was used to preprocess the ECG signals. For every 1 sec of ECG signal, the time-frequency (TF) scalogram was estimated and stacked row wise to obtain a single image from 12 channels, resulting in 10 stacked TF scalograms for each ECG signal. These stacked TF scalograms are fed to the pretrained convolutional neural network (CNN), 1D CNN, and 1D CNN-LSTM (Long short-term memory) models, for arrhythmia classification. The fine-tuned CNN models obtained the best test accuracy of about 98% followed by 95% test accuracy by basic CNN-LSTM in arrhythmia classification.
Side-scan sonar (SSS) imagery presents unique challenges in the classification of man-made objects on the seafloor due to the complex and varied underwater environments. Historically, experts have manually interpreted SSS images, relying on conventional machine learning techniques with hand-crafted features. While Convolutional Neural Networks (CNNs) significantly advanced automated classification in this domain, they often fall short when dealing with diverse seafloor textures, such as rocky or ripple sand bottoms, where false positive rates may increase. Recently, Vision Transformers (ViTs) have shown potential in addressing these limitations by utilizing a self-attention mechanism to capture global information in image patches, offering more flexibility in processing spatial hierarchies. This paper rigorously compares the performance of ViT models alongside commonly used CNN architectures, such as ResNet and ConvNext, for binary classification tasks in SSS imagery. The dataset encompasses diverse geographical seafloor types and is balanced between the presence and absence of man-made objects. ViT-based models exhibit superior classification performance across f1-score, precision, recall, and accuracy metrics, although at the cost of greater computational resources. CNNs, with their inductive biases, demonstrate better computational efficiency, making them suitable for deployment in resource-constrained environments like underwater vehicles. Future research directions include exploring self-supervised learning for ViTs and multi-modal fusion to further enhance performance in challenging underwater environments.
With the rapid progress of China's urbanization, research on the automatic detection of land-use patterns in Chinese cities is of substantial importance. Deep learning is an effective method to extract image features. To take advantage of the deep-learning method in detecting urban land-use patterns, we applied a transfer-learning-based remote-sensing image approach to extract and classify features. Using the Google Tensorflow framework, a powerful convolution neural network (CNN) library was created. First, the transferred model was previously trained on ImageNet, one of the largest object-image data sets, to fully develop the model's ability to generate feature vectors of standard remote-sensing land-cover data sets (UC Merced and WHU-SIRI). Then, a random-forest-based classifier was constructed and trained on these generated vectors to classify the actual urban land-use pattern on the scale of traffic analysis zones (TAZs). To avoid the multi-scale effect of remote-sensing imagery, a large random patch (LRP) method was used. The proposed method could efficiently obtain acceptable accuracy (OA = 0.794, Kappa = 0.737) for the study area. In addition, the results show that the proposed method can effectively overcome the multi-scale effect that occurs in urban land-use classification at the irregular land-parcel level. The proposed method can help planners monitor dynamic urban land use and evaluate the impact of urban-planning schemes.
Publicly available data is essential for the progress of medical image analysis, in particular for crafting machine learning models. Glioma is the most common group of primary brain tumors, and magnetic resonance imaging (MRI) is a widely used modality in their diagnosis and treatment. However, the availability and quality of public datasets for glioma MRI are not well known. In this review, we searched for public datasets for glioma MRI using Google Dataset Search, The Cancer Imaging Archive (TCIA), and Synapse. A total of 28 datasets published between 2005 and May 2024 were found, containing 62019 images from 5515 patients. We analyzed the characteristics of these datasets, such as the origin, size, format, annotation, and accessibility. Additionally, we examined the distribution of tumor types, grades, and stages among the datasets. The implications of the evolution of the WHO classification on tumors of the brain are discussed, in particular the 2021 update that significantly changed the definition of glioblastoma. Additionally, potential research questions that could be explored using these datasets were highlighted, such as tumor evolution through malignant transformation, MRI normalization, and tumor segmentation. Interestingly, only two datasets among the 28 studied reflect the current WHO classification. This review provides a comprehensive overview of the publicly available datasets for glioma MRI currently at our disposal, providing aid to medical image analysis researchers in their decision-making on efficient dataset choice.
Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretraining (CLIP) and Image Caption (IC) into a unified framework, resulting in impressive results. CLIP imposes a bidirectional constraints on global representation of entire images and sentences. Although IC conducts an unidirectional image-to-text generation on local representation, it lacks any constraint on local text-to-image reconstruction, which limits the ability to understand images at a fine-grained level when aligned with texts. To achieve multimodal alignment from both global and local perspectives, this paper proposes Symmetrizing Contrastive Captioners (SyCoCa), which introduces bidirectional interactions on images and texts across the global and local representation levels. Specifically, we expand a Text-Guided Masked Image Modeling (TG-MIM) head based on ITC and IC heads. The improved SyCoCa can further leverage textual cues to reconstruct contextual images and visual cues to predict textual contents. When implementing bidirectional local interactions, the local contents of images tend to be cluttered or unrelated to their textual descriptions. Thus, we employ an attentive masking strategy to select effective image patches for interaction. Extensive experiments on five vision-language tasks, including image-text retrieval, image-captioning, visual question answering, and zero-shot/finetuned image classification, validate the effectiveness of our proposed method.
Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand. Therefore, static models which process all the pixels with an equal amount of computation result in considerable redundancy in terms of time and space consumption. In this paper, we formulate the image recognition problem as a sequential coarse-to-fine feature learning process, mimicking the human visual system. Specifically, the proposed Glance and Focus Network (GFNet) first extracts a quick global representation of the input image at a low resolution scale, and then strategically attends to a series of salient (small) regions to learn finer features. The sequential process naturally facilitates adaptive inference at test time, as it can be terminated once the model is sufficiently confident about its prediction, avoiding further redundant computation. It is worth noting that the problem of locating discriminant regions in our model is formulated as a reinforcement learning task, thus requiring no additional manual annotations other than classification labels. GFNet is general and flexible as it is compatible with any off-the-shelf backbone models (such as MobileNets, EfficientNets and TSM), which can be conveniently deployed as the feature extractor. Extensive experiments on a variety of image classification and video recognition tasks and with various backbone models demonstrate the remarkable efficiency of our method. For example, it reduces the average latency of the highly efficient MobileNet-V3 on an iPhone XS Max by 1.3x without sacrificing accuracy. Code and pre-trained models are available at https://github.com/blackfeather-wang/GFNet-Pytorch.
Compared with traditional model-based fault detection and classification (FDC) methods, deep neural networks (DNN) prove to be effective for the aerospace sensors FDC problems. However, time being consumed in training the DNN is excessive, and explainability analysis for the FDC neural network is still underwhelming. A concept known as imagefication-based intelligent FDC has been studied in recent years. This concept advocates to stack the sensors measurement data into an image format, the sensors FDC issue is then transformed to abnormal regions detection problem on the stacked image, which may well borrow the recent advances in the machine vision vision realm. Although promising results have been claimed in the imagefication-based intelligent FDC researches, due to the low size of the stacked image, small convolutional kernels and shallow DNN layers were used, which hinders the FDC performance. In this paper, we first propose a data augmentation method which inflates the stacked image to a larger size (correspondent to the VGG16 net developed in the machine vision realm). The FDC neural network is then trained via fine-tuning the VGG16 directly. To truncate and compress the FDC net size (hence its running time), we perform model pruning on the fine-tuned net. Class activation mapping (CAM) method is also adopted for explainability analysis of the FDC net to verify its internal operations. Via data augmentation, fine-tuning from VGG16, and model pruning, the FDC net developed in this paper claims an FDC accuracy 98.90% across 4 aircraft at 5 flight conditions (running time 26 ms). The CAM results also verify the FDC net w.r.t. its internal operations.