In past research on self-supervised learning for image classification, the use of rotation as an augmentation has been common. However, relying solely on rotation as a self-supervised transformation can limit the ability of the model to learn rich features from the data. In this paper, we propose a novel approach to self-supervised learning for image classification using several localizable augmentations with the combination of the gating method. Our approach uses flip and shuffle channel augmentations in addition to the rotation, allowing the model to learn rich features from the data. Furthermore, the gated mixture network is used to weigh the effects of each self-supervised learning on the loss function, allowing the model to focus on the most relevant transformations for classification.
Selfie soft biometrics has great potential for various applications ranging from marketing, security and online banking. However, it faces many challenges since there is limited control in data acquisition conditions. This chapter presents a Super-Resolution-Convolutional Neural Networks (SRCNNs) approach that increases the resolution of low quality periocular iris images cropped from selfie images of subject's faces. This work shows that increasing image resolution (2x and 3x) can improve the sex-classification rate when using a Random Forest classifier. The best sex-classification rate was 90.15% for the right and 87.15% for the left eye. This was achieved when images were upscaled from 150x150 to 450x450 pixels. These results compare well with the state of the art and show that when improving image resolution with the SRCNN the sex-classification rate increases. Additionally, a novel selfie database captured from 150 subjects with an iPhone X was created (available upon request).
Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases the optimization like avoiding gradient vanish over the vanilla training. Nevertheless, with the emergence of normalization techniques and residual connection, deep supervision in image classification was gradually phased out. In this paper, we revisit deep supervision for masked image modeling (MIM) that pre-trains a Vision Transformer (ViT) via a mask-and-predict scheme. Experimentally, we find that deep supervision drives the shallower layers to learn more meaningful representations, accelerates model convergence, and expands attention diversities. Our approach, called DeepMIM, significantly boosts the representation capability of each layer. In addition, DeepMIM is compatible with many MIM models across a range of reconstruction targets. For instance, using ViT-B, DeepMIM on MAE achieves 84.2 top-1 accuracy on ImageNet, outperforming MAE by +0.6. By combining DeepMIM with a stronger tokenizer CLIP, our model achieves state-of-the-art performance on various downstream tasks, including image classification (85.6 top-1 accuracy on ImageNet-1K, outperforming MAE-CLIP by +0.8), object detection (52.8 APbox on COCO) and semantic segmentation (53.1 mIoU on ADE20K). Code and models are available at https://github.com/OliverRensu/DeepMIM.
The paper presents the results from a multi-year effort to develop and validate image processing methods for selecting the best physical models based on solar image observations. The approach consists of selecting the physical models based on their agreement with coronal holes extracted from the images. Ultimately, the goal is to use physical models to predict geomagnetic storms. We decompose the problem into three subproblems: (i) coronal hole segmentation based on physical constraints, (ii) matching clusters of coronal holes between different maps, and (iii) physical map classification. For segmenting coronal holes, we develop a multi-modal method that uses segmentation maps from three different methods to initialize a level-set method that evolves the initial coronal hole segmentation to the magnetic boundary. Then, we introduce a new method based on Linear Programming for matching clusters of coronal holes. The final matching is then performed using Random Forests. The methods were carefully validated using consensus maps derived from multiple readers, manual clustering, manual map classification, and method validation for 50 maps. The proposed multi-modal segmentation method significantly outperformed SegNet, U-net, Henney-Harvey, and FCN by providing accurate boundary detection. Overall, the method gave a 95.5% map classification accuracy.
Interpretability is essential for machine learning algorithms in high-stakes application fields such as medical image analysis. However, high-performing black-box neural networks do not provide explanations for their predictions, which can lead to mistrust and suboptimal human-ML collaboration. Post-hoc explanation techniques, which are widely used in practice, have been shown to suffer from severe conceptual problems. Furthermore, as we show in this paper, current explanation techniques do not perform adequately in the multi-label scenario, in which multiple medical findings may co-occur in a single image. We propose Attri-Net, an inherently interpretable model for multi-label classification. Attri-Net is a powerful classifier that provides transparent, trustworthy, and human-understandable explanations. The model first generates class-specific attribution maps based on counterfactuals to identify which image regions correspond to certain medical findings. Then a simple logistic regression classifier is used to make predictions based solely on these attribution maps. We compare Attri-Net to five post-hoc explanation techniques and one inherently interpretable classifier on three chest X-ray datasets. We find that Attri-Net produces high-quality multi-label explanations consistent with clinical knowledge and has comparable classification performance to state-of-the-art classification models.
Industrial image anomaly detection under the setting of one-class classification has significant practical value. However, most existing models struggle to extract separable feature representations when performing feature embedding and struggle to build compact descriptions of normal features when performing one-class classification. One direct consequence of this is that most models perform poorly in detecting logical anomalies which violate contextual relationships. Focusing on more effective and comprehensive anomaly detection, we propose a network based on self-supervised learning and self-attentive graph convolution (SLSG) for anomaly detection. SLSG uses a generative pre-training network to assist the encoder in learning the embedding of normal patterns and the reasoning of position relationships. Subsequently, SLSG introduces the pseudo-prior knowledge of anomaly through simulated abnormal samples. By comparing the simulated anomalies, SLSG can better summarize the normal features and narrow down the hypersphere used for one-class classification. In addition, with the construction of a more general graph structure, SLSG comprehensively models the dense and sparse relationships among elements in the image, which further strengthens the detection of logical anomalies. Extensive experiments on benchmark datasets show that SLSG achieves superior anomaly detection performance, demonstrating the effectiveness of our method.
Abdominal ultrasound imaging has been widely used to assist in the diagnosis and treatment of various abdominal organs. In order to shorten the examination time and reduce the cognitive burden on the sonographers, we present a classification method that combines the deep learning techniques and k-Nearest-Neighbor (k-NN) classification to automatically recognize various abdominal organs in the ultrasound images in real time. Fine-tuned deep neural networks are used in combination with PCA dimension reduction to extract high-level features from raw ultrasound images, and a k-NN classifier is employed to predict the abdominal organ in the image. We demonstrate the effectiveness of our method in the task of ultrasound image classification to automatically recognize six abdominal organs. A comprehensive comparison of different configurations is conducted to study the influence of different feature extractors and classifiers on the classification accuracy. Both quantitative and qualitative results show that with minimal training effort, our method can "lazily" recognize the abdominal organs in the ultrasound images in real time with an accuracy of 96.67%. Our implementation code is publicly available at: https://github.com/LeeKeyu/abdominal_ultrasound_classification.
High-quality labeled datasets are essential for deep learning. Traditional manual annotation methods are not only costly and inefficient but also pose challenges in specialized domains where expert knowledge is needed. Self-supervised methods, despite leveraging unlabeled data for feature extraction, still require hundreds or thousands of labeled instances to guide the model for effective specialized image classification. Current unsupervised learning methods offer automatic classification without prior annotation but often compromise on accuracy. As a result, efficiently procuring high-quality labeled datasets remains a pressing challenge for specialized domain images devoid of annotated data. Addressing this, an unsupervised classification method with three key ideas is introduced: 1) dual-step feature dimensionality reduction using a pre-trained model and manifold learning, 2) a voting mechanism from multiple clustering algorithms, and 3) post-hoc instead of prior manual annotation. This approach outperforms supervised methods in classification accuracy, as demonstrated with fungal image data, achieving 94.1% and 96.7% on public and private datasets respectively. The proposed unsupervised classification method reduces dependency on pre-annotated datasets, enabling a closed-loop for data classification. The simplicity and ease of use of this method will also bring convenience to researchers in various fields in building datasets, promoting AI applications for images in specialized domains.
This paper presents OmniVL, a new foundation model to support both image-language and video-language tasks using one universal architecture. It adopts a unified transformer-based visual encoder for both image and video inputs, and thus can perform joint image-language and video-language pretraining. We demonstrate, for the first time, such a paradigm benefits both image and video tasks, as opposed to the conventional one-directional transfer (e.g., use image-language to help video-language). To this end, we propose a decoupled joint pretraining of image-language and video-language to effectively decompose the vision-language modeling into spatial and temporal dimensions and obtain performance boost on both image and video tasks. Moreover, we introduce a novel unified vision-language contrastive (UniVLC) loss to leverage image-text, video-text, image-label (e.g., image classification), video-label (e.g., video action recognition) data together, so that both supervised and noisily supervised pretraining data are utilized as much as possible. Without incurring extra task-specific adaptors, OmniVL can simultaneously support visual only tasks (e.g., image classification, video action recognition), cross-modal alignment tasks (e.g., image/video-text retrieval), and multi-modal understanding and generation tasks (e.g., image/video question answering, captioning). We evaluate OmniVL on a wide range of downstream tasks and achieve state-of-the-art or competitive results with similar model size and data scale.
Constructing effective representations is a critical but challenging problem in multimedia understanding. The traditional handcraft features often rely on domain knowledge, limiting the performances of exiting methods. This paper discusses a novel computational architecture for general image feature mining, which assembles the primitive filters (i.e. Gabor wavelets) into compositional features in a layer-wise manner. In each layer, we produce a number of base classifiers (i.e. regression stumps) associated with the generated features, and discover informative compositions by using the boosting algorithm. The output compositional features of each layer are treated as the base components to build up the next layer. Our framework is able to generate expressive image representations while inducing very discriminate functions for image classification. The experiments are conducted on several public datasets, and we demonstrate superior performances over state-of-the-art approaches.
Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many available degrees of freedom that alter the image acquisition process (lens focus, exposure, filtering, etc). Here we focus on one such degree of freedom - illumination within a microscope - which can drastically alter information captured by the image sensor. We present a reinforcement learning system that adaptively explores optimal patterns to illuminate specimens for immediate classification. The agent uses a recurrent latent space to encode a large set of variably-illuminated samples and illumination patterns. We train our agent using a reward that balances classification confidence with image acquisition cost. By synthesizing knowledge over multiple snapshots, the agent can classify on the basis of all previous images with higher accuracy than from naively illuminated images, thus demonstrating a smarter way to physically capture task-specific information.
In this paper, we provide a guideline for using the Neural Network Dependability Kit (NNDK) during the development process of NN models, and show how the algorithm is applied in two image classification use cases. The case studies demonstrate the usage of the dependability kit to obtain insights about the NN model and how they informed the development process of the neural network model. After interpreting neural networks via the different metrics available in the NNDK, the developers were able to increase the NNs' accuracy, trust the developed networks, and make them more robust. In addition, we obtained a novel application-oriented technique to provide supporting evidence for an NN's classification result to the user. In the medical image classification use case, it was used to retrieve case images from the training dataset that were similar to the current patient's image and could therefore act as a support for the NN model's decision and aid doctors in interpreting the results.
Despite the success of deep neural networks in medical image classification, the problem remains challenging as data annotation is time-consuming, and the class distribution is imbalanced due to the relative scarcity of diseases. To address this problem, we propose Class-Specific Distribution Alignment (CSDA), a semi-supervised learning framework based on self-training that is suitable to learn from highly imbalanced datasets. Specifically, we first provide a new perspective to distribution alignment by considering the process as a change of basis in the vector space spanned by marginal predictions, and then derive CSDA to capture class-dependent marginal predictions on both labeled and unlabeled data, in order to avoid the bias towards majority classes. Furthermore, we propose a Variable Condition Queue (VCQ) module to maintain a proportionately balanced number of unlabeled samples for each class. Experiments on three public datasets HAM10000, CheXpert and Kvasir show that our method provides competitive performance on semi-supervised skin disease, thoracic disease, and endoscopic image classification tasks.
Convolutional Neural Networks has been implemented in many complex machine learning takes such as image classification, object identification, autonomous vehicle and robotic vision tasks. However, ConvNet architecture efficiency and accuracy depend on a large number of fac- tors. Also, the complex architecture requires a significant amount of data to train and involves with a large number of hyperparameters that increases the computational expenses and difficul- ties. Hence, it is necessary to address the limitations and techniques to overcome the barriers to ensure that the architecture performs well in complex visual tasks. This article is intended to develop an efficient ConvNet architecture for multi-class image categorical classification applica- tion. In the development of the architecture, large pool of grey scale images are taken as input information images and split into training and test datasets. The numerously available technique is implemented to reduce the overfitting and poor generalization of the network. The hyperpa- rameters of determined by Bayesian Optimization with Gaussian Process prior algorithm. ReLu non-linear activation function is implemented after the convolutional layers. Max pooling op- eration is carried out to downsampling the data points in pooling layers. Cross-entropy loss function is used to measure the performance of the architecture where the softmax is used in the classification layer. Mini-batch gradient descent with Adam optimizer algorithm is used for backpropagation. Developed architecture is validated with confusion matrix and classification report.
The inclusion of spatial information into spectral classifiers for fine-resolution hyperspectral imagery has led to significant improvements in terms of classification performance. The task of spectral-spatial hyperspectral image classification has remained challenging because of high intraclass spectrum variability and low interclass spectral variability. This fact has made the extraction of spatial information highly active. In this work, a novel hyperspectral image classification framework using the fusion of dual spatial information is proposed, in which the dual spatial information is built by both exploiting pre-processing feature extraction and post-processing spatial optimization. In the feature extraction stage, an adaptive texture smoothing method is proposed to construct the structural profile (SP), which makes it possible to precisely extract discriminative features from hyperspectral images. The SP extraction method is used here for the first time in the remote sensing community. Then, the extracted SP is fed into a spectral classifier. In the spatial optimization stage, a pixel-level classifier is used to obtain the class probability followed by an extended random walker-based spatial optimization technique. Finally, a decision fusion rule is utilized to fuse the class probabilities obtained by the two different stages. Experiments performed on three data sets from different scenes illustrate that the proposed method can outperform other state-of-the-art classification techniques. In addition, the proposed feature extraction method, i.e., SP, can effectively improve the discrimination between different land covers.
Point cloud understanding is an inherently challenging problem because of the sparse and unordered structure of the point cloud in the 3D space. Recently, Contrastive Vision-Language Pre-training (CLIP) based point cloud classification model i.e. PointCLIP has added a new direction in the point cloud classification research domain. In this method, at first multi-view depth maps are extracted from the point cloud and passed through the CLIP visual encoder. To transfer the 3D knowledge to the network, a small network called an adapter is fine-tuned on top of the CLIP visual encoder. PointCLIP has two limitations. Firstly, the point cloud depth maps lack image information which is essential for tasks like classification and recognition. Secondly, the adapter only relies on the global representation of the multi-view features. Motivated by this observation, we propose a Pretrained Point Cloud to Image Translation Network (PPCITNet) that produces generalized colored images along with additional salient visual cues to the point cloud depth maps so that it can achieve promising performance on point cloud classification and understanding. In addition, we propose a novel viewpoint adapter that combines the view feature processed by each viewpoint as well as the global intertwined knowledge that exists across the multi-view features. The experimental results demonstrate the superior performance of the proposed model over existing state-of-the-art CLIP-based models on ModelNet10, ModelNet40, and ScanobjectNN datasets.
The biggest challenge in the application of deep learning to the medical domain is the availability of training data. Data augmentation is a typical methodology used in machine learning when confronted with a limited data set. In a classical approach image transformations i.e. rotations, cropping and brightness changes are used. In this work, a StyleGAN2-ADA model of Generative Adversarial Networks is trained on the limited COVID-19 chest X-ray image set. After assessing the quality of generated images they are used to increase the training data set improving its balance between classes. We consider the multi-class classification problem of chest X-ray images including the COVID-19 positive class that hasn't been yet thoroughly explored in the literature. Results of transfer learning-based classification of COVID-19 chest X-ray images are presented. The performance of several deep convolutional neural network models is compared. The impact on the detection performance of classical image augmentations i.e. rotations, cropping, and brightness changes are studied. Furthermore, classical image augmentation is compared with GAN-based augmentation. The most accurate model is an EfficientNet-B0 with an accuracy of 90.2 percent, trained on a dataset with a simple class balancing. The GAN augmentation approach is found to be subpar to classical methods for the considered dataset.
Fine-grained classification of cervical cells into different abnormality levels is of great clinical importance but remains very challenging. Contrary to traditional classification methods that rely on hand-crafted or engineered features, convolution neural network (CNN) can classify cervical cells based on automatically learned deep features. However, CNN in previous studies do not involve cell morphological information, and it is unknown whether morphological features can be directly modeled by CNN to classify cervical cells. This paper presents a CNN-based method that combines cell image appearance with cell morphology for classification of cervical cells in Pap smear. The training cervical cell dataset consists of adaptively re-sampled image patches coarsely centered on the nuclei. Several CNN models (AlexNet, GoogleNet, ResNet and DenseNet) pre-trained on ImageNet dataset were fine-tuned on the cervical dataset for comparison. The proposed method is evaluated on the Herlev cervical dataset by five-fold cross-validation at patient level splitting. Results show that by adding cytoplasm and nucleus masks as raw morphological information into appearance-based CNN learning, higher classification accuracies can be achieved in general. Among the four CNN models, GoogleNet fed with both morphological and appearance information obtains the highest classification accuracies of 94.5% for 2-class classification task and 64.5% for 7-class classification task. Our method demonstrates that combining cervical cell morphology with appearance information can provide improved classification performance, which is clinically important for early diagnosis of cervical dysplastic changes.
The visual attributes of cells, such as the nuclear morphology and chromatin openness, are critical for histopathology image analysis. By learning cell-level visual representation, we can obtain a rich mix of features that are highly reusable for various tasks, such as cell-level classification, nuclei segmentation, and cell counting. In this paper, we propose a unified generative adversarial networks architecture with a new formulation of loss to perform robust cell-level visual representation learning in an unsupervised setting. Our model is not only label-free and easily trained but also capable of cell-level unsupervised classification with interpretable visualization, which achieves promising results in the unsupervised classification of bone marrow cellular components. Based on the proposed cell-level visual representation learning, we further develop a pipeline that exploits the varieties of cellular elements to perform histopathology image classification, the advantages of which are demonstrated on bone marrow datasets.
Recently, vision-language pre-trained models have emerged in computational pathology. Previous works generally focused on the alignment of image-text pairs via the contrastive pre-training paradigm. Such pre-trained models have been applied to pathology image classification in zero-shot learning or transfer learning fashion. Herein, we hypothesize that the pre-trained vision-language models can be utilized for quantitative histopathology image analysis through a simple image-to-text retrieval. To this end, we propose a Text-based Quantitative and Explainable histopathology image analysis, which we call TQx. Given a set of histopathology images, we adopt a pre-trained vision-language model to retrieve a word-of-interest pool. The retrieved words are then used to quantify the histopathology images and generate understandable feature embeddings due to the direct mapping to the text description. To evaluate the proposed method, the text-based embeddings of four histopathology image datasets are utilized to perform clustering and classification tasks. The results demonstrate that TQx is able to quantify and analyze histopathology images that are comparable to the prevalent visual models in computational pathology.