Cervical cancer is one of the most deadly and common diseases among women worldwide. It is completely curable if diagnosed in an early stage, but the tedious and costly detection procedure makes it unviable to conduct population-wise screening. Thus, to augment the effort of the clinicians, in this paper, we propose a fully automated framework that utilizes Deep Learning and feature selection using evolutionary optimization for cytology image classification. The proposed framework extracts Deep feature from several Convolution Neural Network models and uses a two-step feature reduction approach to ensure reduction in computation cost and faster convergence. The features extracted from the CNN models form a large feature space whose dimensionality is reduced using Principal Component Analysis while preserving 99% of the variance. A non-redundant, optimal feature subset is selected from this feature space using an evolutionary optimization algorithm, the Grey Wolf Optimizer, thus improving the classification performance. Finally, the selected feature subset is used to train an SVM classifier for generating the final predictions. The proposed framework is evaluated on three publicly available benchmark datasets: Mendeley Liquid Based Cytology (4-class) dataset, Herlev Pap Smear (7-class) dataset, and the SIPaKMeD Pap Smear (5-class) dataset achieving classification accuracies of 99.47%, 98.32% and 97.87% respectively, thus justifying the reliability of the approach. The relevant codes for the proposed approach can be found in: https://github.com/DVLP-CMATERJU/Two-Step-Feature-Enhancement
Rotation-invariance is a desired property of machine-learning models for medical image analysis and in particular for computational pathology applications. We propose a framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks to yield translation and rotation equivariance via the introduction of SE(2)-group convolution layers. This structure enables models to learn feature representations with a discretized orientation dimension that guarantees that their outputs are invariant under a discrete set of rotations. Conventional approaches for rotation invariance rely mostly on data augmentation, but this does not guarantee the robustness of the output when the input is rotated. At that, trained conventional CNNs may require test-time rotation augmentation to reach their full capability. This study is focused on histopathology image analysis applications for which it is desirable that the arbitrary global orientation information of the imaged tissues is not captured by the machine learning models. The proposed framework is evaluated on three different histopathology image analysis tasks (mitosis detection, nuclei segmentation and tumor classification). We present a comparative analysis for each problem and show that consistent increase of performances can be achieved when using the proposed framework.
Vision-language pre-training (VLP) models have shown significant advancements in the medical domain. Yet, most VLP models align raw reports to images at a very coarse level, without modeling fine-grained relationships between anatomical and pathological concepts outlined in reports and the corresponding semantic counterparts in images. To address this problem, we propose a Medical Dual-Stream Language-Image Pre-training (MeDSLIP) framework. Specifically, MeDSLIP establishes vision-language fine-grained alignments via disentangling visual and textual representations into anatomy-relevant and pathology-relevant streams. Moreover, a novel vision-language Prototypical Contr-astive Learning (ProtoCL) method is adopted in MeDSLIP to enhance the alignment within the anatomical and pathological streams. MeDSLIP further employs cross-stream Intra-image Contrastive Learning (ICL) to ensure the consistent coexistence of paired anatomical and pathological concepts within the same image. Such a cross-stream regularization encourages the model to exploit the synchrony between two streams for a more comprehensive representation learning. MeDSLIP is evaluated under zero-shot and supervised fine-tuning settings on three public datasets: NIH CXR14, RSNA Pneumonia, and SIIM-ACR Pneumothorax. Under these settings, MeDSLIP outperforms six leading CNN-based models on classification, grounding, and segmentation tasks.
Frequency analysis is useful for understanding the mechanisms of representation learning in neural networks (NNs). Most research in this area focuses on the learning dynamics of NNs for regression tasks, while little for classification. This study empirically investigates the latter and expands the understanding of frequency shortcuts. First, we perform experiments on synthetic datasets, designed to have a bias in different frequency bands. Our results demonstrate that NNs tend to find simple solutions for classification, and what they learn first during training depends on the most distinctive frequency characteristics, which can be either low- or high-frequencies. Second, we confirm this phenomenon on natural images. We propose a metric to measure class-wise frequency characteristics and a method to identify frequency shortcuts. The results show that frequency shortcuts can be texture-based or shape-based, depending on what best simplifies the objective. Third, we validate the transferability of frequency shortcuts on out-of-distribution (OOD) test sets. Our results suggest that frequency shortcuts can be transferred across datasets and cannot be fully avoided by larger model capacity and data augmentation. We recommend that future research should focus on effective training schemes mitigating frequency shortcut learning.
Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However, this approach can inadvertently introduce noise, induce distribution shifts, and increase the risk of overfitting. In this paper, we propose EntAugment, a tuning-free and adaptive DA framework. Unlike previous work, EntAugment dynamically assesses and adjusts the augmentation magnitudes for each sample during training, leveraging insights into both the inherent complexities of training samples and the evolving status of deep models. Specifically, in EntAugment, the magnitudes are determined by the information entropy derived from the probability distribution obtained by applying the softmax function to the model's output. In addition, to further enhance the efficacy of EntAugment, we introduce a novel entropy regularization term, EntLoss, which complements the EntAugment approach. Theoretical analysis further demonstrates that EntLoss, compared to traditional cross-entropy loss, achieves closer alignment between the model distributions and underlying dataset distributions. Moreover, EntAugment and EntLoss can be utilized separately or jointly. We conduct extensive experiments across multiple image classification tasks and network architectures with thorough comparisons of existing DA methods. Importantly, the proposed methods outperform others without introducing any auxiliary models or noticeable extra computational costs, highlighting both effectiveness and efficiency. Code is available at https://github.com/Jackbrocp/EntAugment.
Learning representations with diversified information remains as an open problem. Towards learning diversified representations, a new approach, termed Information Competing Process (ICP), is proposed in this paper. Aiming to enrich the information carried by feature representations, ICP separates a representation into two parts with different mutual information constraints. The separated parts are forced to accomplish the downstream task independently in a competitive environment which prevents the two parts from learning what each other learned for the downstream task. Such competing parts are then combined synergistically to complete the task. By fusing representation parts learned competitively under different conditions, ICP facilitates obtaining diversified representations which contain rich information. Experiments on image classification and image reconstruction tasks demonstrate the great potential of ICP to learn discriminative and disentangled representations in both supervised and self-supervised learning settings.
Optical imaging is commonly used for both scientific and technological applications across industry and academia. In image sensing, a measurement, such as of an object's position, is performed by computational analysis of a digitized image. An emerging image-sensing paradigm breaks this delineation between data collection and analysis by designing optical components to perform not imaging, but encoding. By optically encoding images into a compressed, low-dimensional latent space suitable for efficient post-analysis, these image sensors can operate with fewer pixels and fewer photons, allowing higher-throughput, lower-latency operation. Optical neural networks (ONNs) offer a platform for processing data in the analog, optical domain. ONN-based sensors have however been limited to linear processing, but nonlinearity is a prerequisite for depth, and multilayer NNs significantly outperform shallow NNs on many tasks. Here, we realize a multilayer ONN pre-processor for image sensing, using a commercial image intensifier as a parallel optoelectronic, optical-to-optical nonlinear activation function. We demonstrate that the nonlinear ONN pre-processor can achieve compression ratios of up to 800:1 while still enabling high accuracy across several representative computer-vision tasks, including machine-vision benchmarks, flow-cytometry image classification, and identification of objects in real scenes. In all cases we find that the ONN's nonlinearity and depth allowed it to outperform a purely linear ONN encoder. Although our experiments are specialized to ONN sensors for incoherent-light images, alternative ONN platforms should facilitate a range of ONN sensors. These ONN sensors may surpass conventional sensors by pre-processing optical information in spatial, temporal, and/or spectral dimensions, potentially with coherent and quantum qualities, all natively in the optical domain.
The prevalence of employing attention mechanisms has brought along concerns on the interpretability of attention distributions. Although it provides insights about how a model is operating, utilizing attention as the explanation of model predictions is still highly dubious. The community is still seeking more interpretable strategies for better identifying local active regions that contribute the most to the final decision. To improve the interpretability of existing attention models, we propose a novel Bilinear Representative Non-Parametric Attention (BR-NPA) strategy that captures the task-relevant human-interpretable information. The target model is first distilled to have higher-resolution intermediate feature maps. From which, representative features are then grouped based on local pairwise feature similarity, to produce finer-grained, more precise attention maps highlighting task-relevant parts of the input. The obtained attention maps are ranked according to the activity level of the compound feature, which provides information regarding the important level of the highlighted regions. The proposed model can be easily adapted in a wide variety of modern deep models, where classification is involved. Extensive quantitative and qualitative experiments showcase more comprehensive and accurate visual explanations compared to state-of-the-art attention models and visualizations methods across multiple tasks including fine-grained image classification, few-shot classification, and person re-identification, without compromising the classification accuracy. The proposed visualization model sheds imperative light on how neural networks `pay their attention' differently in different tasks.
Video classification systems are vulnerable to adversarial attacks, which can create severe security problems in video verification. Current black-box attacks need a large number of queries to succeed, resulting in high computational overhead in the process of attack. On the other hand, attacks with restricted perturbations are ineffective against defenses such as denoising or adversarial training. In this paper, we focus on unrestricted perturbations and propose StyleFool, a black-box video adversarial attack via style transfer to fool the video classification system. StyleFool first utilizes color theme proximity to select the best style image, which helps avoid unnatural details in the stylized videos. Meanwhile, the target class confidence is additionally considered in targeted attacks to influence the output distribution of the classifier by moving the stylized video closer to or even across the decision boundary. A gradient-free method is then employed to further optimize the adversarial perturbations. We carry out extensive experiments to evaluate StyleFool on two standard datasets, UCF-101 and HMDB-51. The experimental results demonstrate that StyleFool outperforms the state-of-the-art adversarial attacks in terms of both the number of queries and the robustness against existing defenses. Moreover, 50% of the stylized videos in untargeted attacks do not need any query since they can already fool the video classification model. Furthermore, we evaluate the indistinguishability through a user study to show that the adversarial samples of StyleFool look imperceptible to human eyes, despite unrestricted perturbations.
Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in GNNs is not well understood. In this paper, we focus on node-wise classification, illustrated with community detection on stochastic block model graphs, and explore the feature evolution through the lens of the "Neural Collapse" (NC) phenomenon. When training instance-wise deep classifiers (e.g. for image classification) beyond the zero training error point, NC demonstrates a reduction in the deepest features' within-class variability and an increased alignment of their class means to certain symmetric structures. We start with an empirical study that shows that a decrease in within-class variability is also prevalent in the node-wise classification setting, however, not to the extent observed in the instance-wise case. Then, we theoretically study this distinction. Specifically, we show that even an "optimistic" mathematical model requires that the graphs obey a strict structural condition in order to possess a minimizer with exact collapse. Interestingly, this condition is viable also for heterophilic graphs and relates to recent empirical studies on settings with improved GNNs' generalization. Furthermore, by studying the gradient dynamics of the theoretical model, we provide reasoning for the partial collapse observed empirically. Finally, we present a study on the evolution of within- and between-class feature variability across layers of a well-trained GNN and contrast the behavior with spectral methods.
Recently a number of studies demonstrated impressive performance on diverse vision-language multi-modal tasks such as image captioning and visual question answering by extending the BERT architecture with multi-modal pre-training objectives. In this work we explore a broad set of multi-modal representation learning tasks in the medical domain, specifically using radiology images and the unstructured report. We propose Medical Vision Language Learner (MedViLL), which adopts a BERT-based architecture combined with a novel multi-modal attention masking scheme to maximize generalization performance for both vision-language understanding tasks (diagnosis classification, medical image-report retrieval, medical visual question answering) and vision-language generation task (radiology report generation). By statistically and rigorously evaluating the proposed model on four downstream tasks with three radiographic image-report datasets (MIMIC-CXR, Open-I, and VQA-RAD), we empirically demonstrate the superior downstream task performance of MedViLL against various baselines, including task-specific architectures. The source code is publicly available at: https://github.com/SuperSupermoon/MedViLL
The article presents a new multi-label comprehensive image dataset from flexible endoscopy, colonoscopy and capsule endoscopy, named ERS. The collection has been labeled according to the full medical specification of 'Minimum Standard Terminology 3.0' (MST 3.0), describing all possible findings in the gastrointestinal tract (104 possible labels), extended with an additional 19 labels useful in common machine learning applications. The dataset contains around 6000 precisely and 115,000 approximately labeled frames from endoscopy videos, 3600 precise and 22,600 approximate segmentation masks, and 1.23 million unlabeled frames from flexible and capsule endoscopy videos. The labeled data cover almost entirely the MST 3.0 standard. The data came from 1520 videos of 1135 patients. Additionally, this paper proposes and describes four exemplary experiments in gastrointestinal image classification task performed using the created dataset. The obtained results indicate the high usefulness and flexibility of the dataset in training and testing machine learning algorithms in the field of endoscopic data analysis.
This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use Vision Transformers (ViTs). Existing works have proposed token reduction approaches to improve the efficiency of ViT-based image classification networks, but these methods are not directly applicable to semantic segmentation, which we address in this work. We observe that, for semantic segmentation, multiple image patches can share a token if they contain the same semantic class, as they contain redundant information. Our approach leverages this by employing an efficient, class-agnostic policy network that predicts if image patches contain the same semantic class, and lets them share a token if they do. With experiments, we explore the critical design choices of CTS and show its effectiveness on the ADE20K, Pascal Context and Cityscapes datasets, various ViT backbones, and different segmentation decoders. With Content-aware Token Sharing, we are able to reduce the number of processed tokens by up to 44%, without diminishing the segmentation quality.
To satisfy the rapidly increasing demands on the large image (2K-8K) super-resolution (SR), prevailing methods follow two independent tracks: 1) accelerate existing networks by content-aware routing, and 2) design better super-resolution networks via token mixer refining. Despite directness, they encounter unavoidable defects (e.g., inflexible route or non-discriminative processing) limiting further improvements of quality-complexity trade-off. To erase the drawbacks, we integrate these schemes by proposing a content-aware mixer (CAMixer), which assigns convolution for simple contexts and additional deformable window-attention for sparse textures. Specifically, the CAMixer uses a learnable predictor to generate multiple bootstraps, including offsets for windows warping, a mask for classifying windows, and convolutional attentions for endowing convolution with the dynamic property, which modulates attention to include more useful textures self-adaptively and improves the representation capability of convolution. We further introduce a global classification loss to improve the accuracy of predictors. By simply stacking CAMixers, we obtain CAMixerSR which achieves superior performance on large-image SR, lightweight SR, and omnidirectional-image SR.
Deep learning models have achieved significant success in various image related tasks. However, they often encounter challenges related to computational complexity and overfitting. In this paper, we propose an efficient approach that leverages polygonal representations of images using dominant points or contour coordinates. By transforming input images into these compact forms, our method significantly reduces computational requirements, accelerates training, and conserves resources making it suitable for real time and resource constrained applications. These representations inherently capture essential image features while filtering noise, providing a natural regularization effect that mitigates overfitting. The resulting lightweight models achieve performance comparable to state of the art methods using full resolution images while enabling deployment on edge devices. Extensive experiments on benchmark datasets validate the effectiveness of our approach in reducing complexity, improving generalization, and facilitating edge computing applications. This work demonstrates the potential of polygonal representations in advancing efficient and scalable deep learning solutions for real world scenarios. The code for the experiments of the paper is provided in https://github.com/salimkhazem/PolygoNet.
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.
Vision transformer architectures have been demonstrated to work very effectively for image classification tasks. Efforts to solve more challenging vision tasks with transformers rely on convolutional backbones for feature extraction. In this paper we investigate the use of a pure transformer architecture (i.e., one with no CNN backbone) for the problem of 2D body pose estimation. We evaluate two ViT architectures on the COCO dataset. We demonstrate that using an encoder-decoder transformer architecture yields state of the art results on this estimation problem.
Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classification and object detection, self-supervised pre-training for fine-grained scenarios is not fully explored. We point out that current contrastive methods are prone to memorizing background/foreground texture and therefore have a limitation in localizing the foreground object. Analysis suggests that learning to extract discriminative texture information and localization are equally crucial for fine-grained self-supervised pre-training. Based on our findings, we introduce cross-view saliency alignment (CVSA), a contrastive learning framework that first crops and swaps saliency regions of images as a novel view generation and then guides the model to localize on foreground objects via a cross-view alignment loss. Extensive experiments on both small- and large-scale fine-grained classification benchmarks show that CVSA significantly improves the learned representation.
Predictive uncertainties in classification tasks are often a consequence of model inadequacy or insufficient training data. In popular applications, such as image processing, we are often required to scrutinise these uncertainties by meaningfully attributing them to input features. This helps to improve interpretability assessments. However, there exist few effective frameworks for this purpose. Vanilla forms of popular methods for the provision of saliency masks, such as SHAP or integrated gradients, adapt poorly to target measures of uncertainty. Thus, state-of-the-art tools instead proceed by creating counterfactual or adversarial feature vectors, and assign attributions by direct comparison to original images. In this paper, we present a novel framework that combines path integrals, counterfactual explanations and generative models, in order to procure attributions that contain few observable artefacts or noise. We evidence that this outperforms existing alternatives through quantitative evaluations with popular benchmarking methods and data sets of varying complexity.
Medical image analysis tasks often focus on regions or structures located in a particular location within the patient's body. Often large parts of the image may not be of interest for the image analysis task. When using deep-learning based approaches, this causes an unnecessary increases the computational burden during inference and raises the chance of errors. In this paper, we introduce CTARR, a novel generic method for CT Anatomical Region Recognition. The method serves as a pre-processing step for any deep learning-based CT image analysis pipeline by automatically identifying the pre-defined anatomical region that is relevant for the follow-up task and removing the rest. It can be used in (i) image segmentation to prevent false positives in anatomically implausible regions and speeding up the inference, (ii) image classification to produce image crops that are consistent in their anatomical context, and (iii) image registration by serving as a fast pre-registration step. Our proposed method is based on atlas registration and provides a fast and robust way to crop any anatomical region encoded as one or multiple bounding box(es) from any unlabeled CT scan of the brain, chest, abdomen and/or pelvis. We demonstrate the utility and robustness of the proposed method in the context of medical image segmentation by evaluating it on six datasets of public segmentation challenges. The foreground voxels in the regions of interest are preserved in the vast majority of cases and tasks (97.45-100%) while taking only fractions of a seconds to compute (0.1-0.21s) on a deep learning workstation and greatly reducing the segmentation runtime (2.0-12.7x). Our code is available at https://github.com/ThomasBudd/ctarr.