Manual identification and classification of pneumonia and COVID-19 infection is a cumbersome process that, if delayed can cause irreversible damage to the patient. We have compiled CT scan images from various sources, namely, from the China Consortium of Chest CT Image Investigation (CC-CCII), the Negin Radiology located at Sari in Iran, an open access COVID-19 repository from Havard dataverse, and Sri Ramachandra University, Chennai, India. The images were preprocessed using various methods such as normalization, sharpening, median filter application, binarizing, and cropping to ensure uniformity while training the models. We present an ensemble classification approach using deep learning and machine learning methods to classify patients with the said diseases. Our ensemble model uses pre-trained networks such as ResNet-18 and ResNet-50 for classification and MobileNetV2 for feature extraction. The features from MobileNetV2 are used by the gradient-boosting classifier for the classification of patients. Using ResNet-18, ResNet-50, and the MobileNetV2 aided gradient boosting classifier, we propose an ensemble model with an accuracy of 98 percent on unseen data.
In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. Specifically, we train a convolutional neural network to learn discriminative features by optimizing two popular versions of the Triplet Loss in order to study their clustering properties under the assumption of noisy labels. Additionally, we propose a new, simple Triplet Loss formulation, which shows desirable properties with respect to formal clustering objectives and outperforms the existing methods. We evaluate all three Triplet loss formulations for K-means and correlation clustering on the CIFAR-10 image classification dataset.
The aim of this work is to provide a semantic scene synthesis from depth image. First, depth image is segmented and each segment is classified in the context of assistive systems using a deep learning network. Second, inspired by the Braille system and the Japanese writing system Kanji, the obtained classes are coded with semantic labels. A semantic scene is then synthesized using the labels and extracted features. Experiments are conducted on noisy, occluded, cropped and incomplete data including acquired depth images of indoor scenes and datasets from the RMRC challenge. The obtained results are reported and discussed.
Convolutional Neural Network is good at image classification. However, it is found to be vulnerable to image quality degradation. Even a small amount of distortion such as noise or blur can severely hamper the performance of these CNN architectures. Most of the work in the literature strives to mitigate this problem simply by fine-tuning a pre-trained CNN on mutually exclusive or a union set of distorted training data. This iterative fine-tuning process with all known types of distortion is exhaustive and the network struggles to handle unseen distortions. In this work, we propose distortion robust DCT-Net, a Discrete Cosine Transform based module integrated into a deep network which is built on top of VGG16. Unlike other works in the literature, DCT-Net is "blind" to the distortion type and level in an image both during training and testing. As a part of the training process, the proposed DCT module discards input information which mostly represents the contribution of high frequencies. The DCT-Net is trained "blindly" only once and applied in generic situation without further retraining. We also extend the idea of traditional dropout and present a training adaptive version of the same. We evaluate our proposed method against Gaussian blur, motion blur, salt and pepper noise, Gaussian noise and speckle noise added to CIFAR-10/100 and ImageNet test sets. Experimental results demonstrate that once trained, DCT-Net not only generalizes well to a variety of unseen image distortions but also outperforms other methods in the literature.
Current AI-based methods do not provide comprehensible physical interpretations of the utilized data, extracted features, and predictions/inference operations. As a result, deep learning models trained using high-resolution satellite imagery lack transparency and explainability and can be merely seen as a black box, which limits their wide-level adoption. Experts need help understanding the complex behavior of AI models and the underlying decision-making process. The explainable artificial intelligence (XAI) field is an emerging field providing means for robust, practical, and trustworthy deployment of AI models. Several XAI techniques have been proposed for image classification tasks, whereas the interpretation of image segmentation remains largely unexplored. This paper offers to bridge this gap by adapting the recent XAI classification algorithms and making them usable for muti-class image segmentation, where we mainly focus on buildings' segmentation from high-resolution satellite images. To benchmark and compare the performance of the proposed approaches, we introduce a new XAI evaluation methodology and metric based on "Entropy" to measure the model uncertainty. Conventional XAI evaluation methods rely mainly on feeding area-of-interest regions from the image back to the pre-trained (utility) model and then calculating the average change in the probability of the target class. Those evaluation metrics lack the needed robustness, and we show that using Entropy to monitor the model uncertainty in segmenting the pixels within the target class is more suitable. We hope this work will pave the way for additional XAI research for image segmentation and applications in the remote sensing discipline.
In this paper, we present a real-time robust multi-view pedestrian detection and tracking system for video surveillance using neural networks which can be used in dynamic environments. The proposed system consists of two phases: multi-view pedestrian detection and tracking. First, pedestrian detection utilizes background subtraction to segment the foreground blob. An adaptive background subtraction method where each of the pixel of input image models as a mixture of Gaussians and uses an on-line approximation to update the model applies to extract the foreground region. The Gaussian distributions are then evaluated to determine which are most likely to result from a background process. This method produces a steady, real-time tracker in outdoor environment that consistently deals with changes of lighting condition, and long-term scene change. Second, the Tracking is performed at two phases: pedestrian classification and tracking the individual subject. A sliding window is applied on foreground binary image to select an input window which is used for selecting the input image patches from actually input frame. The neural networks is used for classification with PHOG features. Finally, a Kalman filter is applied to calculate the subsequent step for tracking that aims at finding the exact position of pedestrians in an input image. The experimental result shows that the proposed approach yields promising performance on multi-view pedestrian detection and tracking on different benchmark datasets.
Prior to the onset of vision, neurons in the developing mammalian retina spontaneously fire in correlated activity patterns known as retinal waves. Experimental evidence suggests that retinal waves strongly influence the emergence of sensory representations before visual experience. We aim to model this early stage of functional development by using movies of neurally active developing retinas as pre-training data for neural networks. Specifically, we pre-train a ResNet-18 with an unsupervised contrastive learning objective (SimCLR) on both simulated and experimentally-obtained movies of retinal waves, then evaluate its performance on image classification tasks. We find that pre-training on retinal waves significantly improves performance on tasks that test object invariance to spatial translation, while slightly improving performance on more complex tasks like image classification. Notably, these performance boosts are realized on held-out natural images even though the pre-training procedure does not include any natural image data. We then propose a geometrical explanation for the increase in network performance, namely that the spatiotemporal characteristics of retinal waves facilitate the formation of separable feature representations. In particular, we demonstrate that networks pre-trained on retinal waves are more effective at separating image manifolds than randomly initialized networks, especially for manifolds defined by sets of spatial translations. These findings indicate that the broad spatiotemporal properties of retinal waves prepare networks for higher order feature extraction.
State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic complexity with image size and increasing computational demands, the researchers are now exploring how to adapt Mamba for computer vision tasks. This paper is the first comprehensive survey aiming to provide an in-depth analysis of Mamba models in the field of computer vision. It begins by exploring the foundational concepts contributing to Mamba's success, including the state space model framework, selection mechanisms, and hardware-aware design. Next, we review these vision mamba models by categorizing them into foundational ones and enhancing them with techniques such as convolution, recurrence, and attention to improve their sophistication. We further delve into the widespread applications of Mamba in vision tasks, which include their use as a backbone in various levels of vision processing. This encompasses general visual tasks, Medical visual tasks (e.g., 2D / 3D segmentation, classification, and image registration, etc.), and Remote Sensing visual tasks. We specially introduce general visual tasks from two levels: High/Mid-level vision (e.g., Object detection, Segmentation, Video classification, etc.) and Low-level vision (e.g., Image super-resolution, Image restoration, Visual generation, etc.). We hope this endeavor will spark additional interest within the community to address current challenges and further apply Mamba models in computer vision.
The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed, however. We address this problem by developing a novel approach to learning a compact binary encoding, which exploits both pair-wise proximity and class-label information on training data set. Exploiting this extra information allows the development of encodings which, although compact, outperform the original high-dimensional features in terms of final classification or retrieval performance. The method is general, in that it is applicable to both non-parametric and parametric learning methods. This generality means that the embedded features are suitable for a wide variety of computer vision tasks, such as image classification and content-based image retrieval. Experimental results demonstrate that the new compact descriptor achieves an accuracy comparable to, and in some cases better than, the visual descriptor in the original space despite being significantly more compact. Moreover, any convex loss function and convex regularization penalty (e.g., $ \ell_p $ norm with $ p \ge 1 $) can be incorporated into the framework, which provides future flexibility.
Neural networks used for image classification tasks in critical applications must be tested with sufficient realistic data to assure their correctness. To effectively test an image classification neural network, one must obtain realistic test data adequate enough to inspire confidence that differences between the implicit requirements and the learned model would be exposed. This raises two challenges: first, an adequate subset of the data points must be carefully chosen to inspire confidence, and second, the implicit requirements must be meaningfully extrapolated to data points beyond those in the explicit training set. This paper proposes a novel framework to address these challenges. Our approach is based on the premise that patterns in a large input data space can be effectively captured in a smaller manifold space, from which similar yet novel test cases---both the input and the label---can be sampled and generated. A variant of Conditional Variational Autoencoder (CVAE) is used for capturing this manifold with a generative function, and a search technique is applied on this manifold space to efficiently find fault-revealing inputs. Experiments show that this approach enables generation of thousands of realistic yet fault-revealing test cases efficiently even for well-trained models.
Reliable skin cancer diagnosis models play an essential role in early screening and medical intervention. Prevailing computer-aided skin cancer classification systems employ deep learning approaches. However, recent studies reveal their extreme vulnerability to adversarial attacks -- often imperceptible perturbations to significantly reduce the performances of skin cancer diagnosis models. To mitigate these threats, this work presents a simple, effective, and resource-efficient defense framework by reverse engineering adversarial perturbations in skin cancer images. Specifically, a multiscale image pyramid is first established to better preserve discriminative structures in the medical imaging domain. To neutralize adversarial effects, skin images at different scales are then progressively diffused by injecting isotropic Gaussian noises to move the adversarial examples to the clean image manifold. Crucially, to further reverse adversarial noises and suppress redundant injected noises, a novel multiscale denoising mechanism is carefully designed that aggregates image information from neighboring scales. We evaluated the defensive effectiveness of our method on ISIC 2019, a largest skin cancer multiclass classification dataset. Experimental results demonstrate that the proposed method can successfully reverse adversarial perturbations from different attacks and significantly outperform some state-of-the-art methods in defending skin cancer diagnosis models.
The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and, finally, we present a new plug-and-play module to model context awareness. We focus on the effect of incorporating circuit motifs found in biological brains to address visual recognition. Our convolutional architecture is inspired by the connectivity of human cortical and subcortical streams, and we implement bottom-up and top-down modulations that mimic the extensive afferent and efferent connections between visual and cognitive areas. Our Contextual Attention Block is simple and effective and can be integrated with any feed-forward neural network. It infers weights that multiply the feature maps according to their causal influence on the scene, modeling the co-occurrence of different objects in the image. We place our module at different bottlenecks to infuse a hierarchical context awareness into the model. We validated our proposals through image classification experiments on benchmark data and found a consistent improvement in performance and the robustness of the produced explanations via class activation. Our code is available at https://github.com/gianlucarloni/CoCoReco.
Long-tailed learning is considered to be an extremely challenging problem in data imbalance learning. It aims to train well-generalized models from a large number of images that follow a long-tailed class distribution. In the medical field, many diagnostic imaging exams such as dermoscopy and chest radiography yield a long-tailed distribution of complex clinical findings. Recently, long-tailed learning in medical image analysis has garnered significant attention. However, the field currently lacks a unified, strictly formulated, and comprehensive benchmark, which often leads to unfair comparisons and inconclusive results. To help the community improve the evaluation and advance, we build a unified, well-structured codebase called Medical OpeN-source Long-taIled ClassifiCAtion (MONICA), which implements over 30 methods developed in relevant fields and evaluated on 12 long-tailed medical datasets covering 6 medical domains. Our work provides valuable practical guidance and insights for the field, offering detailed analysis and discussion on the effectiveness of individual components within the inbuilt state-of-the-art methodologies. We hope this codebase serves as a comprehensive and reproducible benchmark, encouraging further advancements in long-tailed medical image learning. The codebase is publicly available on https://github.com/PyJulie/MONICA.
Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user instruction. These tasks necessitate a multimodal embedding model, which outputs embeddings that combine visual and natural language input. Existing CLIP-based approaches embed images and text independently, and fuse the result. We find that this results in weak interactions between modalities, and poor user control over the representation. We introduce ABC, an open-source multimodal embedding model that uses a vision-language model backbone to deeply integrate image features with natural language instructions. ABC achieves bestfor-size performance on MSCOCO image-to-text retrieval and is the top performing model on classification and VQA tasks in the Massive Multimodal Embedding Benchmark. With a strongly unified vision-language representation, ABC can use natural language to solve subtle and potentially ambiguous visual retrieval problems. To evaluate this capability, we design CtrlBench, a benchmark that requires interleaving textual instructions with image content for correct retrieval. ABC advances the state of multimodal embeddings by offering high-quality representations and flexible natural language control. Our model and datasets are available at our project page.
We design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts. Recent works (CLIP and ALIGN), despite attaining impressive open-vocabulary classification accuracy with image-level caption labels, are unable to segment visual concepts with pixels. We argue that these models miss an important step of visual grouping, which organizes pixels into groups before learning visual-semantic alignments. We propose OpenSeg to address the above issue while still making use of scalable image-level supervision of captions. First, it learns to propose segmentation masks for possible organizations. Then it learns visual-semantic alignments by aligning each word in a caption to one or a few predicted masks. We find the mask representations are the key to support learning image segmentation from captions, making it possible to scale up the dataset and vocabulary sizes. OpenSeg significantly outperforms the recent open-vocabulary method of LSeg by +19.9 mIoU on PASCAL dataset, thanks to its scalability.
Linear Discriminant Analysis (LDA) is a widely-used supervised dimensionality reduction method in computer vision and pattern recognition. In null space based LDA (NLDA), a well-known LDA extension, between-class distance is maximized in the null space of the within-class scatter matrix. However, there are some limitations in NLDA. Firstly, for many data sets, null space of within-class scatter matrix does not exist, thus NLDA is not applicable to those datasets. Secondly, NLDA uses arithmetic mean of between-class distances and gives equal consideration to all between-class distances, which makes larger between-class distances can dominate the result and thus limits the performance of NLDA. In this paper, we propose a harmonic mean based Linear Discriminant Analysis, Multi-Class Discriminant Analysis (MCDA), for image classification, which minimizes the reciprocal of weighted harmonic mean of pairwise between-class distance. More importantly, MCDA gives higher priority to maximize small between-class distances. MCDA can be extended to multi-label dimension reduction. Results on 7 single-label data sets and 4 multi-label data sets show that MCDA has consistently better performance than 10 other single-label approaches and 4 other multi-label approaches in terms of classification accuracy, macro and micro average F1 score.
In this paper, we introduce a deep learning model to classify children as either healthy or potentially autistic with 94.6% accuracy using Deep Learning. Autistic patients struggle with social skills, repetitive behaviors, and communication, both verbal and nonverbal. Although the disease is considered to be genetic, the highest rates of accurate diagnosis occur when the child is tested on behavioral characteristics and facial features. Patients have a common pattern of distinct facial deformities, allowing researchers to analyze only an image of the child to determine if the child has the disease. While there are other techniques and models used for facial analysis and autism classification on their own, our proposal bridges these two ideas allowing classification in a cheaper, more efficient method. Our deep learning model uses MobileNet and two dense layers in order to perform feature extraction and image classification. The model is trained and tested using 3,014 images, evenly split between children with autism and children without it. 90% of the data is used for training, and 10% is used for testing. Based on our accuracy, we propose that the diagnosis of autism can be done effectively using only a picture. Additionally, there may be other diseases that are similarly diagnosable.
Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The augmentation enables contrast with another view of a single image but enlarges training time and memory usage. To exploit the strength of multi-views while avoiding the high computation cost, we introduce a multi-exit architecture that outputs multiple features of a single image in a single-viewed framework. To this end, we propose Self-Contrastive (SelfCon) learning, which self-contrasts within multiple outputs from the different levels of a single network. The multi-exit architecture efficiently replaces multi-augmented images and leverages various information from different layers of a network. We demonstrate that SelfCon learning improves the classification performance of the encoder network, and empirically analyze its advantages in terms of the single-view and the sub-network. Furthermore, we provide theoretical evidence of the performance increase based on the mutual information bound. For ImageNet classification on ResNet-50, SelfCon improves accuracy by +0.6% with 59% memory and 48% time of Supervised Contrastive learning, and a simple ensemble of multi-exit outputs boosts performance up to +1.5%. Our code is available at https://github.com/raymin0223/self-contrastive-learning.
Interpreting a large number of neurons in deep learning is difficult. Our proposed `CLAssifier-DECoder' architecture (ClaDec) facilitates the understanding of the output of an arbitrary layer of neurons or subsets thereof. It uses a decoder that transforms the incomprehensible representation of the given neurons to a representation that is more similar to the domain a human is familiar with. In an image recognition problem, one can recognize what information (or concepts) a layer maintains by contrasting reconstructed images of ClaDec with those of a conventional auto-encoder(AE) serving as reference. An extension of ClaDec allows trading comprehensibility and fidelity. We evaluate our approach for image classification using convolutional neural networks. We show that reconstructed visualizations using encodings from a classifier capture more relevant classification information than conventional AEs. This holds although AEs contain more information on the original input. Our user study highlights that even non-experts can identify a diverse set of concepts contained in images that are relevant (or irrelevant) for the classifier. We also compare against saliency based methods that focus on pixel relevance rather than concepts. We show that ClaDec tends to highlight more relevant input areas to classification though outcomes depend on classifier architecture. Code is at \url{https://github.com/JohnTailor/ClaDec}
Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical relationships and spatial features, show potential in addressing this issue. Nevertheless, traditional capsule networks often underperform due to their shallow structures, and deeper variants lack hierarchical architectures, thereby compromising interpretability. This paper introduces a novel capsule network, ParseCaps, which utilizes the sparse axial attention routing and parse convolutional capsule layer to form a parse-tree-like structure, enhancing both depth and interpretability. Firstly, sparse axial attention routing optimizes connections between child and parent capsules, as well as emphasizes the weight distribution across instantiation parameters of parent capsules. Secondly, the parse convolutional capsule layer generates capsule predictions aligning with the parse tree. Finally, based on the loss design that is effective whether concept ground truth exists or not, ParseCaps advances interpretability by associating each dimension of the global capsule with a comprehensible concept, thereby facilitating clinician trust and understanding of the model's classification results. Experimental results on CE-MRI, PH$^2$, and Derm7pt datasets show that ParseCaps not only outperforms other capsule network variants in classification accuracy, redundancy reduction and robustness, but also provides interpretable explanations, regardless of the availability of concept labels.