Magnetic Resonance Imaging (MRI) suffers from several artifacts, the most common of which are motion artifacts. These artifacts often yield images that are of non-diagnostic quality. To detect such artifacts, images are prospectively evaluated by experts for their diagnostic quality, which necessitates patient-revisits and rescans whenever non-diagnostic quality scans are encountered. This motivates the need to develop an automated framework capable of accessing medical image quality and detecting diagnostic and non-diagnostic images. In this paper, we explore several convolutional neural network-based frameworks for medical image quality assessment and investigate several challenges therein.
Intracranial hemorrhage (ICH) is a life-threatening medical emergency that requires timely and accurate diagnosis for effective treatment and improved patient survival rates. While deep learning techniques have emerged as the leading approach for medical image analysis and processing, the most commonly employed supervised learning often requires large, high-quality annotated datasets that can be costly to obtain, particularly for pixel/voxel-wise image segmentation. To address this challenge and facilitate ICH treatment decisions, we introduce a novel weakly supervised method for ICH segmentation, utilizing a Swin transformer trained on an ICH classification task with categorical labels. Our approach leverages a hierarchical combination of head-wise gradient-infused self-attention maps to generate accurate image segmentation. Additionally, we conducted an exploratory study on different learning strategies and showed that binary ICH classification has a more positive impact on self-attention maps compared to full ICH subtyping. With a mean Dice score of 0.44, our technique achieved similar ICH segmentation performance as the popular U-Net and Swin-UNETR models with full supervision and outperformed a similar weakly supervised approach using GradCAM, demonstrating the excellent potential of the proposed framework in challenging medical image segmentation tasks. Our code is available at https://github.com/HealthX-Lab/HGI-SAM.
In this paper, we present a novel method to automatically classify medical images that learns and leverages weak causal signals in the image. Our framework consists of a convolutional neural network backbone and a causality-extractor module that extracts cause-effect relationships between feature maps that can inform the model on the appearance of a feature in one place of the image, given the presence of another feature within some other place of the image. To evaluate the effectiveness of our approach in low-data scenarios, we train our causality-driven architecture in a One-shot learning scheme, where we propose a new meta-learning procedure entailing meta-training and meta-testing tasks that are designed using related classes but at different levels of granularity. We conduct binary and multi-class classification experiments on a publicly available dataset of prostate MRI images. To validate the effectiveness of the proposed causality-driven module, we perform an ablation study and conduct qualitative assessments using class activation maps to highlight regions strongly influencing the network's decision-making process. Our findings show that causal relationships among features play a crucial role in enhancing the model's ability to discern relevant information and yielding more reliable and interpretable predictions. This would make it a promising approach for medical image classification tasks.
Deep learning has made significant progress in computer vision, specifically in image classification, object detection, and semantic segmentation. The skip connection has played an essential role in the architecture of deep neural networks,enabling easier optimization through residual learning during the training stage and improving accuracy during testing. Many neural networks have inherited the idea of residual learning with skip connections for various tasks, and it has been the standard choice for designing neural networks. This survey provides a comprehensive summary and outlook on the development of skip connections in deep neural networks. The short history of skip connections is outlined, and the development of residual learning in deep neural networks is surveyed. The effectiveness of skip connections in the training and testing stages is summarized, and future directions for using skip connections in residual learning are discussed. Finally, we summarize seminal papers, source code, models, and datasets that utilize skip connections in computer vision, including image classification, object detection, semantic segmentation, and image reconstruction. We hope this survey could inspire peer researchers in the community to develop further skip connections in various forms and tasks and the theory of residual learning in deep neural networks. The project page can be found at https://github.com/apple1986/Residual_Learning_For_Images
Quantitative image analysis often depends on accurate classification of pixels through a segmentation process. However, imaging artifacts such as the partial volume effect and sensor noise complicate the classification process. These effects increase the pixel intensity variance of each constituent class, causing intensities from one class to overlap with another. This increased variance makes threshold based segmentation methods insufficient due to ambiguous overlap regions in the pixel intensity distributions. The class ambiguity becomes even more complex for systems with more than two constituents, such as unsaturated moist granular media. In this paper, we propose an image processing workflow that improves segmentation accuracy for multiphase systems. First, the ambiguous transition regions between classes are identified and removed, which allows for global thresholding of single-class regions. Then the transition regions are classified using a distance function, and finally both segmentations are combined into one classified image. This workflow includes three methodologies for identifying transition pixels and we demonstrate on a variety of synthetic images that these approaches are able to accurately separate the ambiguous transition pixels from the single-class regions. For situations with typical amounts of image noise, misclassification errors and area differences calculated between each class of the synthetic images and the resultant segmented images range from 0.69-1.48% and 0.01-0.74%, respectively, showing the segmentation accuracy of this approach. We demonstrate that we are able to accurately segment x-ray microtomography images of moist granular media using these computationally efficient methodologies.
The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundary. For instance, when training with cross-entropy loss, examples with higher likelihoods (i.e., well-classified examples) contribute smaller gradients in back-propagation. However, we theoretically show that this common practice hinders representation learning, energy optimization, and margin growth. To counteract this deficiency, we propose to reward well-classified examples with additive bonuses to revive their contribution to the learning process. This counterexample theoretically addresses these three issues. We empirically support this claim by directly verifying the theoretical results or significant performance improvement with our counterexample on diverse tasks, including image classification, graph classification, and machine translation. Furthermore, this paper shows that we can deal with complex scenarios, such as imbalanced classification, OOD detection, and applications under adversarial attacks because our idea can solve these three issues. Code is available at: https://github.com/lancopku/well-classified-examples-are-underestimated.
We present ktrain, a low-code Python library that makes machine learning more accessible and easier to apply. As a wrapper to TensorFlow and many other libraries (e.g., transformers, scikit-learn, stellargraph), it is designed to make sophisticated, state-of-the-art machine learning models simple to build, train, inspect, and apply by both beginners and experienced practitioners. Featuring modules that support text data (e.g., text classification, sequence tagging, open-domain question-answering), vision data (e.g., image classification), graph data (e.g., node classification, link prediction), and tabular data, ktrain presents a simple unified interface enabling one to quickly solve a wide range of tasks in as little as three or four "commands" or lines of code.
While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous representations of the audio signal together with large architectures, fine-tuned from large datasets. By utilizing the inherited lightweight nature of audio and novel audio augmentations, we were able to present an efficient end-to-end network with strong generalization ability. Experiments on a variety of sound classification sets demonstrate the effectiveness and robustness of our approach, by achieving state-of-the-art results in various settings. Public code is available at: \href{https://github.com/Alibaba-MIIL/AudioClassfication}{this http url}
Referring image segmentation aims to segment the image region of interest according to the given language expression, which is a typical multi-modal task. Existing methods either adopt the pixel classification-based or the learnable query-based framework for mask generation, both of which are insufficient to deal with various text-image pairs with a fix number of parametric prototypes. In this work, we propose an end-to-end framework built on transformer to perform Linguistic query-Guided mask generation, dubbed LGFormer. It views the linguistic features as query to generate a specialized prototype for arbitrary input image-text pair, thus generating more consistent segmentation results. Moreover, we design several cross-modal interaction modules (\eg, vision-language bidirectional attention module, VLBA) in both encoder and decoder to achieve better cross-modal alignment.
Recently, test-time adaptation has attracted wide interest in the context of vision-language models for image classification. However, to the best of our knowledge, the problem is completely overlooked in dense prediction tasks such as Open-Vocabulary Semantic Segmentation (OVSS). In response, we propose a novel TTA method tailored to adapting VLMs for segmentation during test time. Unlike TTA methods for image classification, our Multi-Level and Multi-Prompt (MLMP) entropy minimization integrates features from intermediate vision-encoder layers and is performed with different text-prompt templates at both the global CLS token and local pixel-wise levels. Our approach could be used as plug-and-play for any segmentation network, does not require additional training data or labels, and remains effective even with a single test sample. Furthermore, we introduce a comprehensive OVSS TTA benchmark suite, which integrates a rigorous evaluation protocol, seven segmentation datasets, and 15 common corruptions, with a total of 82 distinct test scenarios, establishing a standardized and comprehensive testbed for future TTA research in open-vocabulary segmentation. Our experiments on this suite demonstrate that our segmentation-tailored method consistently delivers significant gains over direct adoption of TTA classification baselines.
In the recent years, researchers proposed a number of successful methods to perform out-of-distribution (OOD) detection in deep neural networks (DNNs). So far the scope of the highly accurate methods has been limited to image level classification tasks. However, attempts for generally applicable methods beyond classification did not attain similar performance. In this paper, we address this limitation by proposing a simple yet effective task-agnostic OOD detection method. We estimate the probability density functions (pdfs) of intermediate features of a pre-trained DNN by performing kernel density estimation (KDE) on the training dataset. As direct application of KDE to feature maps is hindered by their high dimensionality, we use a set of lower-dimensional marginalized KDE models instead of a single high-dimensional one. At test time, we evaluate the pdfs on a test sample and produce a confidence score that indicates the sample is OOD. The use of KDE eliminates the need for making simplifying assumptions about the underlying feature pdfs and makes the proposed method task-agnostic. We perform extensive experiments on classification tasks using benchmark datasets for OOD detection. Additionally, we perform experiments on medical image segmentation tasks using brain MRI datasets. The results demonstrate that the proposed method consistently achieves high OOD detection performance in both classification and segmentation tasks and improves state-of-the-art in almost all cases. Code is available at \url{https://github.com/eerdil/task_agnostic_ood}
Software testing is often hindered where it is impossible or impractical to determine the correctness of the behaviour or output of the software under test (SUT), a situation known as the oracle problem. An example of an area facing the oracle problem is automatic image classification, using machine learning to classify an input image as one of a set of predefined classes. An approach to software testing that alleviates the oracle problem is metamorphic testing (MT). While traditional software testing examines the correctness of individual test cases, MT instead examines the relations amongst multiple executions of test cases and their outputs. These relations are called metamorphic relations (MRs): if an MR is found to be violated, then a fault must exist in the SUT. This paper examines the problem of classifying images containing visually hidden markers called Artcodes, and applies MT to verify and enhance the trained classifiers. This paper further examines two MRs, Separation and Occlusion, and reports on their capability in verifying the image classification using one-way analysis of variance (ANOVA) in conjunction with three other statistical analysis methods: t-test (for unequal variances), Kruskal-Wallis test, and Dunnett's test. In addition to our previously-studied classifier, that used Random Forests, we introduce a new classifier that uses a support vector machine, and present its MR-augmented version. Experimental evaluations across a number of performance metrics show that the augmented classifiers can achieve better performance than non-augmented classifiers. This paper also analyses how the enhanced performance is obtained.
Many image transformations can be modeled by image operators that are characterized by pixel-wise local functions defined on a finite support window. In image operator learning, these functions are estimated from training data using machine learning techniques. Input size is usually a critical issue when using learning algorithms, and it limits the size of practicable windows. We propose the use of convolutional neural networks (CNNs) to overcome this limitation. The problem of removing staff-lines in music score images is chosen to evaluate the effects of window and convolutional mask sizes on the learned image operator performance. Results show that the CNN based solution outperforms previous ones obtained using conventional learning algorithms or heuristic algorithms, indicating the potential of CNNs as base classifiers in image operator learning. The implementations will be made available on the TRIOSlib project site.
Apple is one of the remarkable fresh fruit that contains a high degree of nutritious and medicinal value. Hand harvesting of apples by seasonal farmworkers increases physical damages on the surface of these fruits, which causes a great loss in marketing quality. The main objective of this study is focused on designing a robust vision algorithm for robotic apple harvesters. The proposed algorithm is able to recognize and classify 4-classes of objects found in an orchard scene including apples, leaves, trunk and branches, and sky into two apples and non-apples classes. 100 digital images of Red Delicious apples and 100 digital images of Golden Delicious apples were selected among 1000 captured images of apples from 18 apple gardens in West Azerbaijan, Iran. An image processing algorithm is proposed for segmentation and extraction of the image classes based on the color characteristics of mentioned classes. Invariant-Momentums were chosen as the extracted features from the segmented classes, e.g. apples. Multilayer Feedforward Neural Networks, MFNNs, were used as an artificial intelligence tool for the recognition and classification of image classes.
Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and more computational resources compared to convolutional neural networks (CNNs), owing to the quadratic complexity of their self-attention mechanism. We propose a linear attention-convolution hybrid architecture -- Convolutional X-formers for Vision (CXV) -- to overcome these limitations. We replace the quadratic attention with linear attention mechanisms, such as Performer, Nystr\"omformer, and Linear Transformer, to reduce its GPU usage. Inductive prior for image data is provided by convolutional sub-layers, thereby eliminating the need for class token and positional embeddings used by the ViTs. We also propose a new training method where we use two different optimizers during different phases of training and show that it improves the top-1 image classification accuracy across different architectures. CXV outperforms other architectures, token mixers (e.g. ConvMixer, FNet and MLP Mixer), transformer models (e.g. ViT, CCT, CvT and hybrid Xformers), and ResNets for image classification in scenarios with limited data and GPU resources (cores, RAM, power).
The detection of induced pluripotent stem cell (iPSC) colonies often needs the precise extraction of the colony features. However, existing computerized systems relied on segmentation of contours by preprocessing for classifying the colony conditions were task-extensive. To maximize the efficiency in categorizing colony conditions, we propose a multiple instance learning (MIL) in weakly supervised settings. It is designed in a single model to produce weak segmentation and classification of colonies without using finely labeled samples. As a single model, we employ a U-net-like convolution neural network (CNN) to train on binary image-level labels for MIL colonies classification. Furthermore, to specify the object of interest we used a simple post-processing method. The proposed approach is compared over conventional methods using five-fold cross-validation and receiver operating characteristic (ROC) curve. The maximum accuracy of the MIL-net is 95%, which is 15 % higher than the conventional methods. Furthermore, the ability to interpret the location of the iPSC colonies based on the image level label without using a pixel-wise ground truth image is more appealing and cost-effective in colony condition recognition.
We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small images to learn from large-scale language supervision efficiently, and finetune the model with high-resolution data in the end. Since the complexity of the vision transformer heavily depends on input image size, our approach significantly reduces the training resource requirements both in theory and in practice. Using the same batch size and training epoch, RECLIP achieves highly competitive zero-shot classification and image-text retrieval accuracy with 6 to 8x less computational resources and 7 to 9x fewer FLOPs than the baseline. Compared to the state-of-the-art contrastive learning methods, RECLIP demonstrates 5 to 59x training resource savings while maintaining highly competitive zero-shot classification and retrieval performance. Finally, RECLIP matches the state of the art in transfer learning to open-vocabulary detection tasks, achieving 32 APr on LVIS. We hope this work will pave the path for the broader research community to explore language supervised pretraining in resource-friendly settings.
The rapid proliferation of digital content and the ever-growing need for precise object recognition and segmentation have driven the advancement of cutting-edge techniques in the field of object classification and segmentation. This paper introduces "Learn and Search", a novel approach for object lookup that leverages the power of contrastive learning to enhance the efficiency and effectiveness of retrieval systems. In this study, we present an elegant and innovative methodology that integrates deep learning principles and contrastive learning to tackle the challenges of object search. Our extensive experimentation reveals compelling results, with "Learn and Search" achieving superior Similarity Grid Accuracy, showcasing its efficacy in discerning regions of utmost similarity within an image relative to a cropped image. The seamless fusion of deep learning and contrastive learning to address the intricacies of object identification not only promises transformative applications in image recognition, recommendation systems, and content tagging but also revolutionizes content-based search and retrieval. The amalgamation of these techniques, as exemplified by "Learn and Search," represents a significant stride in the ongoing evolution of methodologies in the dynamic realm of object classification and segmentation.
Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge. Existing methods aim to tackle this problem by locating and aligning relevant local features. However, the high intra-class variability in real-world images poses significant challenges in locating semantically relevant local regions under few-shot settings. Drawing inspiration from the human's complementary learning system, which excels at rapidly capturing and integrating semantic features from limited examples, we propose the generalization-optimized Systems Consolidation Adaptive Memory Dual-Network, SCAM-Net. This approach simulates the systems consolidation of complementary learning system with an adaptive memory module, which successfully addresses the difficulty of identifying meaningful features in few-shot scenarios. Specifically, we construct a Hippocampus-Neocortex dual-network that consolidates structured representation of each category, the structured representation is then stored and adaptively regulated following the generalization optimization principle in a long-term memory inside Neocortex. Extensive experiments on benchmark datasets show that the proposed model has achieved state-of-the-art performance.
3D point-clouds and 2D images are different visual representations of the physical world. While human vision can understand both representations, computer vision models designed for 2D image and 3D point-cloud understanding are quite different. Our paper explores the potential of transferring 2D model architectures and weights to understand 3D point-clouds, by empirically investigating the feasibility of the transfer, the benefits of the transfer, and shedding light on why the transfer works. We discover that we can indeed use the same architecture and pretrained weights of a neural net model to understand both images and point-clouds. Specifically, we transfer the image-pretrained model to a point-cloud model by copying or inflating the weights. We find that finetuning the transformed image-pretrained models (FIP) with minimal efforts -- only on input, output, and normalization layers -- can achieve competitive performance on 3D point-cloud classification, beating a wide range of point-cloud models that adopt task-specific architectures and use a variety of tricks. When finetuning the whole model, the performance improves even further. Meanwhile, FIP improves data efficiency, reaching up to 10.0 top-1 accuracy percent on few-shot classification. It also speeds up the training of point-cloud models by up to 11.1x for a target accuracy (e.g., 90 % accuracy). Lastly, we provide an explanation of the image to point-cloud transfer from the aspect of neural collapse. The code is available at: \url{https://github.com/chenfengxu714/image2point}.