Capsule networks aim to parse images into a hierarchy of objects, parts and relations. While promising, they remain limited by an inability to learn effective low level part descriptions. To address this issue we propose a way to learn primary capsule encoders that detect atomic parts from a single image. During training we exploit motion as a powerful perceptual cue for part definition, with an expressive decoder for part generation within a layered image model with occlusion. Experiments demonstrate robust part discovery in the presence of multiple objects, cluttered backgrounds, and occlusion. The part decoder infers the underlying shape masks, effectively filling in occluded regions of the detected shapes. We evaluate FlowCapsules on unsupervised part segmentation and unsupervised image classification.
Face detection and identification is the most difficult and often used task in Artificial Intelligence systems. The goal of this study is to present and compare the results of several face detection and recognition algorithms used in the system. This system begins with a training image of a human, then continues on to the test image, identifying the face, comparing it to the trained face, and finally classifying it using OpenCV classifiers. This research will discuss the most effective and successful tactics used in the system, which are implemented using Python, OpenCV, and Matplotlib. It may also be used in locations with CCTV, such as public spaces, shopping malls, and ATM booths.
Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling.
Data augmentation has proven to be effective in training neural networks. Recently, a method called RandAug was proposed, randomly selecting data augmentation techniques from a predefined search space. RandAug has demonstrated significant performance improvements for image-related tasks while imposing minimal computational overhead. However, no prior research has explored the application of RandAug specifically for audio data augmentation, which converts audio into an image-like pattern. To address this gap, we introduce AudRandAug, an adaptation of RandAug for audio data. AudRandAug selects data augmentation policies from a dedicated audio search space. To evaluate the effectiveness of AudRandAug, we conducted experiments using various models and datasets. Our findings indicate that AudRandAug outperforms other existing data augmentation methods regarding accuracy performance.
We assess the benefit of including an image inpainting filter before passing damaged images into a classification neural network. For this we employ a modified Cahn-Hilliard equation as an image inpainting filter, which is solved via a finite volume scheme with reduced computational cost and adequate properties for energy stability and boundedness. The benchmark dataset employed here is MNIST, which consists of binary images of handwritten digits and is a standard dataset to validate image-processing methodologies. We train a neural network based of dense layers with the training set of MNIST, and subsequently we contaminate the test set with damage of different types and intensities. We then compare the prediction accuracy of the neural network with and without applying the Cahn-Hilliard filter to the damaged images test. Our results quantify the significant improvement of damaged-image prediction due to applying the Cahn-Hilliard filter, which for specific damages can increase up to 50% and is in general advantageous for low to moderate damage.
Understanding 3D medical image volumes is a critical task in the medical domain. However, existing 3D convolution and transformer-based methods have limited semantic understanding of an image volume and also need a large set of volumes for training. Recent advances in multi-modal large language models (MLLMs) provide a new and promising way to understand images with the help of text descriptions. However, most current MLLMs are designed for 2D natural images. To enhance the 3D medical image understanding with 2D MLLMs, we propose a novel pre-training framework called Med3DInsight, which marries existing 3D image encoders with 2D MLLMs and bridges them via a designed Plane-Slice-Aware Transformer (PSAT) module. Extensive experiments demonstrate our SOTA performance on two downstream segmentation and classification tasks, including three public datasets with CT and MRI modalities and comparison to more than ten baselines. Med3DInsight can be easily integrated into any current 3D medical image understanding network and improves its performance by a good margin.
While standard Empirical Risk Minimization (ERM) training is proven effective for image classification on in-distribution data, it fails to perform well on out-of-distribution samples. One of the main sources of distribution shift for image classification is the compositional nature of images. Specifically, in addition to the main object or component(s) determining the label, some other image components usually exist, which may lead to the shift of input distribution between train and test environments. More importantly, these components may have spurious correlations with the label. To address this issue, we propose Decompose-and-Compose (DaC), which improves robustness to correlation shift by a compositional approach based on combining elements of images. Based on our observations, models trained with ERM usually highly attend to either the causal components or the components having a high spurious correlation with the label (especially in datapoints on which models have a high confidence). In fact, according to the amount of spurious correlation and the easiness of classification based on the causal or non-causal components, the model usually attends to one of these more (on samples with high confidence). Following this, we first try to identify the causal components of images using class activation maps of models trained with ERM. Afterward, we intervene on images by combining them and retraining the model on the augmented data, including the counterfactual ones. Along with its high interpretability, this work proposes a group-balancing method by intervening on images without requiring group labels or information regarding the spurious features during training. The method has an overall better worst group accuracy compared to previous methods with the same amount of supervision on the group labels in correlation shift.
Convolutional neural networks (CNNs) have been applied to learn spatial features for high-resolution (HR) synthetic aperture radar (SAR) image classification. However, there has been little work on integrating the unique statistical distributions of SAR images which can reveal physical properties of terrain objects, into CNNs in a supervised feature learning framework. To address this problem, a novel end-to-end supervised classification method is proposed for HR SAR images by considering both spatial context and statistical features. First, to extract more effective spatial features from SAR images, a new deep spatial context encoder network (DSCEN) is proposed, which is a lightweight structure and can be effectively trained with a small number of samples. Meanwhile, to enhance the diversity of statistics, the nonstationary joint statistical model (NS-JSM) is adopted to form the global statistical features. Specifically, SAR images are transformed into the Gabor wavelet domain and the produced multi-subbands magnitudes and phases are modeled by the log-normal and uniform distribution. The covariance matrix is further utilized to capture the inter-scale and intra-scale nonstationary correlation between the statistical subbands and make the joint statistical features more compact and distinguishable. Considering complementary advantages, a feature fusion network (Fusion-Net) base on group compression and smooth normalization is constructed to embed the statistical features into the spatial features and optimize the fusion feature representation. As a result, our model can learn the discriminative features and improve the final classification performance. Experiments on four HR SAR images validate the superiority of the proposed method over other related algorithms.
Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience. However, training deep learning models requires massive volume of data. An insufficient training data will cause serious overfitting problem and degrade the classification accuracy. To cope with small dataset, data augmentation has been widely used in image processing to expand the dataset and improve the robustness of deep learning models. However, in wireless communication areas, the effect of different data augmentation methods on radio modulation classification has not been studied yet. In this paper, we evaluate different data augmentation methods via a state-of-the-art deep learning-based modulation classifier. Based on the characteristics of modulated signals, three augmentation methods are considered, i.e., rotation, flip, and Gaussian noise, which can be applied in both training phase and inference phase of the deep learning algorithm. Numerical results show that all three augmentation methods can improve the classification accuracy. Among which, the rotation augmentation method outperforms the flip method, both of which achieve higher classification accuracy than the Gaussian noise method. Given only 12.5% of training dataset, a joint rotation and flip augmentation policy can achieve even higher classification accuracy than the baseline with initial 100% training dataset without augmentation. Furthermore, with data augmentation, radio modulation categories can be successfully classified using shorter radio samples, leading to a simplified deep learning model and shorter the classification response time.
Background. Cardiac dominance classification is essential for SYNTAX score estimation, which is a tool used to determine the complexity of coronary artery disease and guide patient selection toward optimal revascularization strategy. Objectives. Cardiac dominance classification algorithm based on the analysis of right coronary artery (RCA) angiograms using neural network Method. We employed convolutional neural network ConvNext and Swin transformer for 2D image (frames) classification, along with a majority vote for cardio angiographic view classification. An auxiliary network was also used to detect irrelevant images which were then excluded from the data set. Our data set consisted of 828 angiographic studies, 192 of them being patients with left dominance. Results. 5-fold cross validation gave the following dominance classification metrics (p=95%): macro recall=93.1%, accuracy=93.5%, macro F1=89.2%. The most common case in which the model regularly failed was RCA occlusion, as it requires utilization of LCA information. Another cause for false prediction is a small diameter combined with poor quality cardio angiographic view. In such cases, cardiac dominance classification can be complex and may require discussion among specialists to reach an accurate conclusion. Conclusion. The use of machine learning approaches to classify cardiac dominance based on RCA alone has been shown to be successful with satisfactory accuracy. However, for higher accuracy, it is necessary to utilize LCA information in the case of an occluded RCA and detect cases where there is high uncertainty.
Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not only introduce poor alignment between the modalities but also a missed opportunity to exploit rich self-supervision through existing temporal content in the data. In this work, we explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model. It is designed to be versatile to arising challenges such as pose variations and missing input images across time. The resulting model excels on downstream tasks both in single- and multi-image setups, achieving state-of-the-art performance on (I) progression classification, (II) phrase grounding, and (III) report generation, whilst offering consistent improvements on disease classification and sentence-similarity tasks. We release a novel multi-modal temporal benchmark dataset, MS-CXR-T, to quantify the quality of vision-language representations in terms of temporal semantics. Our experimental results show the advantages of incorporating prior images and reports to make most use of the data.
This paper focuses on answering fill-in-the-blank style multiple choice questions from the Visual Madlibs dataset. Previous approaches to Visual Question Answering (VQA) have mainly used generic image features from networks trained on the ImageNet dataset, despite the wide scope of questions. In contrast, our approach employs features derived from networks trained for specialized tasks of scene classification, person activity prediction, and person and object attribute prediction. We also present a method for selecting sub-regions of an image that are relevant for evaluating the appropriateness of a putative answer. Visual features are computed both from the whole image and from local regions, while sentences are mapped to a common space using a simple normalized canonical correlation analysis (CCA) model. Our results show a significant improvement over the previous state of the art, and indicate that answering different question types benefits from examining a variety of image cues and carefully choosing informative image sub-regions.
Deep Learning (DL) has become prevalent in today's image processing research due to its power and versatility. It has dominated the Single Image Super-Resolution (SISR) field with its ability to obtain High-Resolution (HR) images from their Low-Resolution (LR) counterparts, particularly using Generative Adversarial Networks (GANs). Interest in SISR comes from its potential to increase the performance of supplementary image processing tasks such as object detection, localization, and classification. This research applies a multi-agent Reinforcement Learning (RL) algorithm to SISR, creating an advanced ensemble approach for combining powerful GANs. In our implementation each agent chooses a particular action from a fixed action set comprised of results from existing GAN SISR algorithms to update its pixel values. The pixel-wise or patch-wise arrangement of agents and rewards encourages the algorithm to learn a strategy to increase the resolution of an image by choosing the best pixel values from each option.
Contrast enhancement is very important in terms of assessing images in an objective way. Contrast enhancement is also significant for various algorithms including supervised and unsupervised algorithms for accurate classification of samples. Some contrast enhancement algorithms solve this problem by addressing the low contrast issue. Mean and variance based sub-image histogram equalization (MVSIHE) algorithm is one of these contrast enhancements methods proposed in the literature. It has different parameters which need to be tuned in order to achieve optimum results. With this motivation, in this study, we employed one of the most recent optimization algorithms, namely, coot optimization algorithm (COA) for selecting appropriate parameters for the MVSIHE algorithm. Blind/referenceless image spatial quality evaluator (BRISQUE) and natural image quality evaluator (NIQE) metrics are used for evaluating fitness of the coot swarm population. The results show that the proposed method can be used in the field of biomedical image processing.
As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision applications (CV), such as image recognition. There are several potential problems with convolutional neural networks (CNNs) that can be solved with ViTs. For image coding tasks like compression, super-resolution, segmentation, and denoising, different variants of the ViTs are used. The purpose of this survey is to present the first application of ViTs in CV. The survey is the first of its kind on ViTs for CVs to the best of our knowledge. In the first step, we classify different CV applications where ViTs are applicable. CV applications include image classification, object detection, image segmentation, image compression, image super-resolution, image denoising, and anomaly detection. Our next step is to review the state-of-the-art in each category and list the available models. Following that, we present a detailed analysis and comparison of each model and list its pros and cons. After that, we present our insights and lessons learned for each category. Moreover, we discuss several open research challenges and future research directions.
The explosive growth of digital images and the widespread availability of image editing tools have made image manipulation detection an increasingly critical challenge. Current deep learning-based manipulation detection methods excel in achieving high image-level classification accuracy, they often fall short in terms of interpretability and localization of manipulated regions. Additionally, the absence of pixel-wise annotations in real-world scenarios limits the existing fully-supervised manipulation localization techniques. To address these challenges, we propose a novel weakly-supervised approach that integrates activation maps generated by image-level manipulation detection networks with segmentation maps from pre-trained models. Specifically, we build on our previous image-level work named WCBnet to produce multi-view feature maps which are subsequently fused for coarse localization. These coarse maps are then refined using detailed segmented regional information provided by pre-trained segmentation models (such as DeepLab, SegmentAnything and PSPnet), with Bayesian inference employed to enhance the manipulation localization. Experimental results demonstrate the effectiveness of our approach, highlighting the feasibility to localize image manipulations without relying on pixel-level labels.
In standard classification, we typically treat class categories as independent of one-another. In many problems, however, we would be neglecting the natural relations that exist between categories, which are often dictated by an underlying biological or physical process. In this work, we propose novel formulations of the classification problem, based on a realization that the assumption of class-independence is a limiting factor that leads to the requirement of more training data. First, we propose manual ways to reduce our data needs by reintroducing knowledge about problem-specific interclass relations into the training process. Second, we propose a general approach to jointly learn categorical label representations that can implicitly encode natural interclass relations, alleviating the need for strong prior assumptions, which are not always available. We demonstrate this in the domain of medical images, where access to large amounts of labelled data is not trivial. Specifically, our experiments show the advantages of this approach in the classification of Intravenous Contrast enhancement phases in CT images, which encapsulate multiple interesting inter-class relations.
In histopathology, intelligent diagnosis of Whole Slide Images (WSIs) is essential for automating and objectifying diagnoses, reducing the workload of pathologists. However, diagnostic models often face the challenge of forgetting previously learned data during incremental training on datasets from different sources. To address this issue, we propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification. Our framework introduces two key components into the common MIL model architecture. First, it leverages microscopic pathological prior to select more accurate and diverse representative patches for MIL. Secondly, it trains separate classification heads for each task and uses macroscopic pathological prior knowledge, treating the thumbnail as a prompt guide (PG) to select the appropriate classification head. We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets. PaGMIL achieves a better balance between the performance of the current task and the retention of previous tasks, outperforming other continual learning methods. Our code will be open-sourced upon acceptance.
When human annotators are given a choice about what to label in an image, they apply their own subjective judgments on what to ignore and what to mention. We refer to these noisy "human-centric" annotations as exhibiting human reporting bias. Examples of such annotations include image tags and keywords found on photo sharing sites, or in datasets containing image captions. In this paper, we use these noisy annotations for learning visually correct image classifiers. Such annotations do not use consistent vocabulary, and miss a significant amount of the information present in an image; however, we demonstrate that the noise in these annotations exhibits structure and can be modeled. We propose an algorithm to decouple the human reporting bias from the correct visually grounded labels. Our results are highly interpretable for reporting "what's in the image" versus "what's worth saying." We demonstrate the algorithm's efficacy along a variety of metrics and datasets, including MS COCO and Yahoo Flickr 100M. We show significant improvements over traditional algorithms for both image classification and image captioning, doubling the performance of existing methods in some cases.
In medical imaging, chromosome straightening plays a significant role in the pathological study of chromosomes and in the development of cytogenetic maps. Whereas different approaches exist for the straightening task, typically geometric algorithms are used whose outputs are characterized by jagged edges or fragments with discontinued banding patterns. To address the flaws in the geometric algorithms, we propose a novel framework based on image-to-image translation to learn a pertinent mapping dependence for synthesizing straightened chromosomes with uninterrupted banding patterns and preserved details. In addition, to avoid the pitfall of deficient input chromosomes, we construct an augmented dataset using only one single curved chromosome image for training models. Based on this framework, we apply two popular image-to-image translation architectures, U-shape networks and conditional generative adversarial networks, to assess its efficacy. Experiments on a dataset comprised of 642 real-world chromosomes demonstrate the superiority of our framework, as compared to the geometric method in straightening performance, by rendering realistic and continued chromosome details. Furthermore, our straightened results improve the chromosome classification by 0.98%-1.39% mean accuracy.