Capturing global contextual information plays a critical role in breast ultrasound (BUS) image classification. Although convolutional neural networks (CNNs) have demonstrated reliable performance in tumor classification, they have inherent limitations for modeling global and long-range dependencies due to the localized nature of convolution operations. Vision Transformers have an improved capability of capturing global contextual information but may distort the local image patterns due to the tokenization operations. In this study, we proposed a hybrid multitask deep neural network called Hybrid-MT-ESTAN, designed to perform BUS tumor classification and segmentation using a hybrid architecture composed of CNNs and Swin Transformer components. The proposed approach was compared to nine BUS classification methods and evaluated using seven quantitative metrics on a dataset of 3,320 BUS images. The results indicate that Hybrid-MT-ESTAN achieved the highest accuracy, sensitivity, and F1 score of 82.7%, 86.4%, and 86.0%, respectively.
This paper addresses the problem of ranking pre-trained models for object detection and image classification. Selecting the best pre-trained model by fine-tuning is an expensive and time-consuming task. Previous works have proposed transferability estimation based on features extracted by the pre-trained models. We argue that quantifying whether the target dataset is in-distribution (IND) or out-of-distribution (OOD) for the pre-trained model is an important factor in the transferability estimation. To this end, we propose ETran, an energy-based transferability assessment metric, which includes three scores: 1) energy score, 2) classification score, and 3) regression score. We use energy-based models to determine whether the target dataset is OOD or IND for the pre-trained model. In contrast to the prior works, ETran is applicable to a wide range of tasks including classification, regression, and object detection (classification+regression). This is the first work that proposes transferability estimation for object detection task. Our extensive experiments on four benchmarks and two tasks show that ETran outperforms previous works on object detection and classification benchmarks by an average of 21% and 12%, respectively, and achieves SOTA in transferability assessment.
Clinical decision making from magnetic resonance imaging (MRI) combines complementary information from multiple MRI sequences (defined as 'modalities'). MRI image registration aims to geometrically 'pair' diagnoses from different modalities, time points and slices. Both intra- and inter-modality MRI registration are essential components in clinical MRI settings. Further, an MRI image processing pipeline that can address both afine and non-rigid registration is critical, as both types of deformations may be occuring in real MRI data scenarios. Unlike image classification, explainability is not commonly addressed in image registration deep learning (DL) methods, as it is challenging to interpet model-data behaviours against transformation fields. To properly address this, we incorporate Grad-CAM-based explainability frameworks in each major component of our unsupervised multi-modal and multi-organ image registration DL methodology. We previously demonstrated that we were able to reach superior performance (against the current standard Syn method). In this work, we show that our DL model becomes fully explainable, setting the framework to generalise our approach on further medical imaging data.
Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical in order to ensure the safety and robustness of critical AI tasks. However, most evasion attacks are difficult to deploy against a majority of AI systems because they have focused on image domain with only few constraints. An image is composed of homogeneous, numerical, continuous, and independent features, unlike many other input types to AI systems used in practice. Furthermore, some input types include additional semantic and functional constraints that must be observed to generate realistic adversarial inputs. In this work, we propose a new framework to enable the generation of adversarial inputs irrespective of the input type and task domain. Given an input and a set of pre-defined input transformations, our framework discovers a sequence of transformations that result in a semantically correct and functional adversarial input. We demonstrate the generality of our approach on several diverse machine learning tasks with various input representations. We also show the importance of generating adversarial examples as they enable the deployment of mitigation techniques.
Fine-grained image classification (FGIC) is a challenging task in computer vision for due to small visual differences among inter-subcategories, but, large intra-class variations. Deep learning methods have achieved remarkable success in solving FGIC. In this paper, we propose a fusion approach to address FGIC by combining global texture with local patch-based information. The first pipeline extracts deep features from various fixed-size non-overlapping patches and encodes features by sequential modelling using the long short-term memory (LSTM). Another path computes image-level textures at multiple scales using the local binary patterns (LBP). The advantages of both streams are integrated to represent an efficient feature vector for image classification. The method is tested on eight datasets representing the human faces, skin lesions, food dishes, marine lives, etc. using four standard backbone CNNs. Our method has attained better classification accuracy over existing methods with notable margins.
This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems. With comparable performance on the image classification task, it allows for the modification of the weights via a continuous group of symmetry. This is a significant shift from traditional models where the architecture and weights are essentially fixed. We wish to promote the (internal) symmetry as a new desirable property for a neural network, and to draw attention to the PDE perspective in analyzing and interpreting ConvNets in the broader Deep Learning community.
AI alignment refers to models acting towards human-intended goals, preferences, or ethical principles. Given that most large-scale deep learning models act as black boxes and cannot be manually controlled, analyzing the similarity between models and humans can be a proxy measure for ensuring AI safety. In this paper, we focus on the models' visual perception alignment with humans, further referred to as AI-human visual alignment. Specifically, we propose a new dataset for measuring AI-human visual alignment in terms of image classification, a fundamental task in machine perception. In order to evaluate AI-human visual alignment, a dataset should encompass samples with various scenarios that may arise in the real world and have gold human perception labels. Our dataset consists of three groups of samples, namely Must-Act (i.e., Must-Classify), Must-Abstain, and Uncertain, based on the quantity and clarity of visual information in an image and further divided into eight categories. All samples have a gold human perception label; even Uncertain (severely blurry) sample labels were obtained via crowd-sourcing. The validity of our dataset is verified by sampling theory, statistical theories related to survey design, and experts in the related fields. Using our dataset, we analyze the visual alignment and reliability of five popular visual perception models and seven abstention methods. Our code and data is available at https://github.com/jiyounglee-0523/VisAlign.
The rapid spread of COVID-19 has necessitated efficient and accurate diagnostic methods. Computed Tomography (CT) scan images have emerged as a valuable tool for detecting the disease. In this article, we present a novel deep learning approach for automated COVID-19 CT scan classification where a modified Xception model is proposed which incorporates a newly designed channel attention mechanism and weighted global average pooling to enhance feature extraction thereby improving classification accuracy. The channel attention module selectively focuses on informative regions within each channel, enabling the model to learn discriminative features for COVID-19 detection. Experiments on a widely used COVID-19 CT scan dataset demonstrate a very good accuracy of 96.99% and show its superiority to other state-of-the-art techniques. This research can contribute to the ongoing efforts in using artificial intelligence to combat current and future pandemics and can offer promising and timely solutions for efficient medical image analysis tasks.
This paper seeks to address the dense labeling problems where a significant fraction of the dataset can be pruned without sacrificing much accuracy. We observe that, on standard medical image segmentation benchmarks, the loss gradient norm-based metrics of individual training examples applied in image classification fail to identify the important samples. To address this issue, we propose a data pruning method by taking into consideration the training dynamics on target regions using Dynamic Average Dice (DAD) score. To the best of our knowledge, we are among the first to address the data importance in dense labeling tasks in the field of medical image analysis, making the following contributions: (1) investigating the underlying causes with rigorous empirical analysis, and (2) determining effective data pruning approach in dense labeling problems. Our solution can be used as a strong yet simple baseline to select important examples for medical image segmentation with combined data sources.
Medical image classification models are frequently trained using training datasets derived from multiple data sources. While leveraging multiple data sources is crucial for achieving model generalization, it is important to acknowledge that the diverse nature of these sources inherently introduces unintended confounders and other challenges that can impact both model accuracy and transparency. A notable confounding factor in medical image classification, particularly in musculoskeletal image classification, is skeletal maturation-induced bone growth observed during adolescence. We train a deep learning model using a Covid-19 chest X-ray dataset and we showcase how this dataset can lead to spurious correlations due to unintended confounding regions. eXplanation Based Learning (XBL) is a deep learning approach that goes beyond interpretability by utilizing model explanations to interactively unlearn spurious correlations. This is achieved by integrating interactive user feedback, specifically feature annotations. In our study, we employed two non-demanding manual feedback mechanisms to implement an XBL-based approach for effectively eliminating these spurious correlations. Our results underscore the promising potential of XBL in constructing robust models even in the presence of confounding factors.
Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs and outputs usually imply more tokens involved in computations. Directly removing the less attentive tokens has been discussed for the image classification task but can not be extended to semantic segmentation since a dense prediction is required for every patch. To this end, this work introduces a Dynamic Token Pruning (DToP) method based on the early exit of tokens for semantic segmentation. Motivated by the coarse-to-fine segmentation process by humans, we naturally split the widely adopted auxiliary-loss-based network architecture into several stages, where each auxiliary block grades every token's difficulty level. We can finalize the prediction of easy tokens in advance without completing the entire forward pass. Moreover, we keep $k$ highest confidence tokens for each semantic category to uphold the representative context information. Thus, computational complexity will change with the difficulty of the input, akin to the way humans do segmentation. Experiments suggest that the proposed DToP architecture reduces on average $20\% - 35\%$ of computational cost for current semantic segmentation methods based on plain vision transformers without accuracy degradation.
Breast Cancer (BC) is among women's most lethal health concerns. Early diagnosis can alleviate the mortality rate by helping patients make efficient treatment decisions. Human Epidermal Growth Factor Receptor (HER2) has become one the most lethal subtype of BC. According to the College of American Pathologists American Society of Clinical Oncology (CAP/ASCO), the severity level of HER2 expression can be classified between 0 and 3+ range. HER2 can be detected effectively from immunohistochemical (IHC) and, hematoxylin & eosin (HE) images of different classes such as 0, 1+, 2+, and 3+. An ensemble approach integrated with threshold filtered single instance evaluation (SIE) technique has been proposed in this study to diagnose BC from the multi-categorical expression of HER2 subtypes. Initially, DenseNet201 and Xception have been ensembled into a single classifier as feature extractors with an effective combination of global average pooling, dropout layer, dense layer with a swish activation function, and l2 regularizer, batch normalization, etc. After that, extracted features has been processed through single instance evaluation (SIE) to determine different confidence levels and adjust decision boundary among the imbalanced classes. This study has been conducted on the BC immunohistochemical (BCI) dataset, which is classified by pathologists into four stages of HER2 BC. This proposed approach known as DenseNet201-Xception-SIE with a threshold value of 0.7 surpassed all other existing state-of-art models with an accuracy of 97.12%, precision of 97.15%, and recall of 97.68% on H&E data and, accuracy of 97.56%, precision of 97.57%, and recall of 98.00% on IHC data respectively, maintaining momentous improvement. Finally, Grad-CAM and Guided Grad-CAM have been employed in this study to interpret, how TL-based model works on the histopathology dataset and make decisions from the data.
Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like understanding capabilities to achieve better performance is still an open question. This paper draws inspiration from the human visual perception process: when classifying an object, humans first infer contextual attributes (e.g., background and orientation) which help separate the foreground object from the background, and then classify the object based on this information. Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features. We also observe that CLIP itself can reasonably infer the attributes from an image. With these observations, we propose a training-free, two-step zero-shot classification method PerceptionCLIP. Given an image, it first infers contextual attributes (e.g., background) and then performs object classification conditioning on them. Our experiments show that PerceptionCLIP achieves better generalization, group robustness, and interoperability. Our code is available at https://github.com/umd-huang-lab/perceptionCLIP
Deep spiking neural networks (SNNs) are promising neural networks for their model capacity from deep neural network architecture and energy efficiency from SNNs' operations. To train deep SNNs, recently, spatio-temporal backpropagation (STBP) with surrogate gradient was proposed. Although deep SNNs have been successfully trained with STBP, they cannot fully utilize spike information. In this work, we proposed gradient scaling with local spike information, which is the relation between pre- and post-synaptic spikes. Considering the causality between spikes, we could enhance the training performance of deep SNNs. According to our experiments, we could achieve higher accuracy with lower spikes by adopting the gradient scaling on image classification tasks, such as CIFAR10 and CIFAR100.
The difficulty of the fine-grained image classification mainly comes from a shared overall appearance across classes. Thus, recognizing discriminative details, such as eyes and beaks for birds, is a key in the task. However, this is particularly challenging when training data is limited. To address this, we propose Task Discrepancy Maximization (TDM), a task-oriented channel attention method tailored for fine-grained few-shot classification with two novel modules Support Attention Module (SAM) and Query Attention Module (QAM). SAM highlights channels encoding class-wise discriminative features, while QAM assigns higher weights to object-relevant channels of the query. Based on these submodules, TDM produces task-adaptive features by focusing on channels encoding class-discriminative details and possessed by the query at the same time, for accurate class-sensitive similarity measure between support and query instances. While TDM influences high-level feature maps by task-adaptive calibration of channel-wise importance, we further introduce Instance Attention Module (IAM) operating in intermediate layers of feature extractors to instance-wisely highlight object-relevant channels, by extending QAM. The merits of TDM and IAM and their complementary benefits are experimentally validated in fine-grained few-shot classification tasks. Moreover, IAM is also shown to be effective in coarse-grained and cross-domain few-shot classifications.
In recent years, deep neural networks are yielding better performance in image classification tasks. However, the increasing complexity of datasets and the demand for improved performance necessitate the exploration of innovative techniques. The present work proposes a new deep neural network (called as, T-Fusion Net) that augments multiple localizations based spatial attention. This attention mechanism allows the network to focus on relevant image regions, improving its discriminative power. A homogeneous ensemble of the said network is further used to enhance image classification accuracy. For ensembling, the proposed approach considers multiple instances of individual T-Fusion Net. The model incorporates fuzzy max fusion to merge the outputs of individual nets. The fusion process is optimized through a carefully chosen parameter to strike a balance on the contributions of the individual models. Experimental evaluations on benchmark Covid-19 (SARS-CoV-2 CT scan) dataset demonstrate the effectiveness of the proposed T-Fusion Net as well as its ensemble. The proposed T-Fusion Net and the homogeneous ensemble model exhibit better performance, as compared to other state-of-the-art methods, achieving accuracy of 97.59% and 98.4%, respectively.
Images are loaded with semantic information that pertains to real-world ontologies: dog breeds share mammalian similarities, food pictures are often depicted in domestic environments, and so on. However, when training machine learning models for image classification, the relative similarities amongst object classes are commonly paired with one-hot-encoded labels. According to this logic, if an image is labelled as 'spoon', then 'tea-spoon' and 'shark' are equally wrong in terms of training loss. To overcome this limitation, we explore the integration of additional goals that reflect ontological and semantic knowledge, improving model interpretability and trustworthiness. We suggest a generic approach that allows to derive an additional loss term starting from any kind of semantic information about the classification label. First, we show how to apply our approach to ontologies and word embeddings, and discuss how the resulting information can drive a supervised learning process. Second, we use our semantically enriched loss to train image classifiers, and analyse the trade-offs between accuracy, mistake severity, and learned internal representations. Finally, we discuss how this approach can be further exploited in terms of explainability and adversarial robustness. Code repository: https://github.com/S1M0N38/semantic-encodings
The limited availability of labeled chest X-ray datasets is a significant bottleneck in the development of medical imaging methods. Self-supervised learning (SSL) can mitigate this problem by training models on unlabeled data. Furthermore, self-supervised pretraining has yielded promising results in visual recognition of natural images but has not been given much consideration in medical image analysis. In this work, we propose a self-supervised method, DINO-CXR, which is a novel adaptation of a self-supervised method, DINO, based on a vision transformer for chest X-ray classification. A comparative analysis is performed to show the effectiveness of the proposed method for both pneumonia and COVID-19 detection. Through a quantitative analysis, it is also shown that the proposed method outperforms state-of-the-art methods in terms of accuracy and achieves comparable results in terms of AUC and F-1 score while requiring significantly less labeled data.
In this study, we demonstrate the application of a hybrid Vision Transformer (ViT) model, pretrained on ImageNet, on an electroencephalogram (EEG) regression task. Despite being originally trained for image classification tasks, when fine-tuned on EEG data, this model shows a notable increase in performance compared to other models, including an identical architecture ViT trained without the ImageNet weights. This discovery challenges the traditional understanding of model generalization, suggesting that Transformer models pretrained on seemingly unrelated image data can provide valuable priors for EEG regression tasks with an appropriate fine-tuning pipeline. The success of this approach suggests that the features extracted by ViT models in the context of visual tasks can be readily transformed for the purpose of EEG predictive modeling. We recommend utilizing this methodology not only in neuroscience and related fields, but generally for any task where data collection is limited by practical, financial, or ethical constraints. Our results illuminate the potential of pretrained models on tasks that are clearly distinct from their original purpose.
Human body-pose estimation is a complex problem in computer vision. Recent research interests have been widened specifically on the Sports, Yoga, and Dance (SYD) postures for maintaining health conditions. The SYD pose categories are regarded as a fine-grained image classification task due to the complex movement of body parts. Deep Convolutional Neural Networks (CNNs) have attained significantly improved performance in solving various human body-pose estimation problems. Though decent progress has been achieved in yoga postures recognition using deep learning techniques, fine-grained sports, and dance recognition necessitates ample research attention. However, no benchmark public image dataset with sufficient inter-class and intra-class variations is available yet to address sports and dance postures classification. To solve this limitation, we have proposed two image datasets, one for 102 sport categories and another for 12 dance styles. Two public datasets, Yoga-82 which contains 82 classes and Yoga-107 represents 107 classes are collected for yoga postures. These four SYD datasets are experimented with the proposed deep model, SYD-Net, which integrates a patch-based attention (PbA) mechanism on top of standard backbone CNNs. The PbA module leverages the self-attention mechanism that learns contextual information from a set of uniform and multi-scale patches and emphasizes discriminative features to understand the semantic correlation among patches. Moreover, random erasing data augmentation is applied to improve performance. The proposed SYD-Net has achieved state-of-the-art accuracy on Yoga-82 using five base CNNs. SYD-Net's accuracy on other datasets is remarkable, implying its efficiency. Our Sports-102 and Dance-12 datasets are publicly available at https://sites.google.com/view/syd-net/home.