This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localization maps as pseudo labels. Building upon the observation that the attended regions of the one-class token in the standard vision transformer can contribute to a class-agnostic localization map, we explore the potential of the transformer model to capture class-specific attention for class-discriminative object localization by learning multiple class tokens. We introduce a Multi-Class Token transformer, which incorporates multiple class tokens to enable class-aware interactions with the patch tokens. To achieve this, we devise a class-aware training strategy that establishes a one-to-one correspondence between the output class tokens and the ground-truth class labels. Moreover, a Contrastive-Class-Token (CCT) module is proposed to enhance the learning of discriminative class tokens, enabling the model to better capture the unique characteristics and properties of each class. As a result, class-discriminative object localization maps can be effectively generated by leveraging the class-to-patch attentions associated with different class tokens. To further refine these localization maps, we propose the utilization of patch-level pairwise affinity derived from the patch-to-patch transformer attention. Furthermore, the proposed framework seamlessly complements the Class Activation Mapping (CAM) method, resulting in significantly improved WSSS performance on the PASCAL VOC 2012 and MS COCO 2014 datasets. These results underline the importance of the class token for WSSS.
Current referring video object segmentation (R-VOS) techniques extract conditional kernels from encoded (low-resolution) vision-language features to segment the decoded high-resolution features. We discovered that this causes significant feature drift, which the segmentation kernels struggle to perceive during the forward computation. This negatively affects the ability of segmentation kernels. To address the drift problem, we propose a Spectrum-guided Multi-granularity (SgMg) approach, which performs direct segmentation on the encoded features and employs visual details to further optimize the masks. In addition, we propose Spectrum-guided Cross-modal Fusion (SCF) to perform intra-frame global interactions in the spectral domain for effective multimodal representation. Finally, we extend SgMg to perform multi-object R-VOS, a new paradigm that enables simultaneous segmentation of multiple referred objects in a video. This not only makes R-VOS faster, but also more practical. Extensive experiments show that SgMg achieves state-of-the-art performance on four video benchmark datasets, outperforming the nearest competitor by 2.8% points on Ref-YouTube-VOS. Our extended SgMg enables multi-object R-VOS, runs about 3 times faster while maintaining satisfactory performance. Code is available at https://github.com/bo-miao/SgMg.
Neuromorphic computing and spiking neural networks aim to leverage biological inspiration to achieve greater energy efficiency and computational power beyond traditional von Neumann architectured machines. In particular, spiking neural networks hold the potential to advance artificial intelligence as the basis of third-generation neural networks. Aided by developments in memristive and compute-in-memory technologies, neuromorphic computing hardware is transitioning from laboratory prototype devices to commercial chipsets; ushering in an era of low-power computing. As a nexus of biological, computing, and material sciences, the literature surrounding these concepts is vast, varied, and somewhat distinct from artificial neural network sources. This article uses bibliometric analysis to survey the last 22 years of literature, seeking to establish trends in publication and citation volumes (III-A); analyze impactful authors, journals and institutions (III-B); generate an introductory reading list (III-C); survey collaborations between countries, institutes and authors (III-D), and to analyze changes in research topics over the years (III-E). We analyze literature data from the Clarivate Web of Science using standard bibliometric methods. By briefly introducing the most impactful literature in this field from the last two decades, we encourage AI practitioners and researchers to look beyond contemporary technologies toward a potentially spiking future of computing.
This study investigates the effectiveness of Explainable Artificial Intelligence (XAI) techniques in predicting suicide risks and identifying the dominant causes for such behaviours. Data augmentation techniques and ML models are utilized to predict the associated risk. Furthermore, SHapley Additive exPlanations (SHAP) and correlation analysis are used to rank the importance of variables in predictions. Experimental results indicate that Decision Tree (DT), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) models achieve the best results while DT has the best performance with an accuracy of 95:23% and an Area Under Curve (AUC) of 0.95. As per SHAP results, anger problems, depression, and social isolation are the leading variables in predicting the risk of suicide, and patients with good incomes, respected occupations, and university education have the least risk. Results demonstrate the effectiveness of machine learning and XAI framework for suicide risk prediction, and they can assist psychiatrists in understanding complex human behaviours and can also assist in reliable clinical decision-making.
Data are the core of deep learning (DL), and the quality of data significantly affects the performance of DL models. However, high-quality and well-annotated databases are hard or even impossible to acquire for use in many applications, such as structural risk estimation and medical diagnosis, which is an essential barrier that blocks the applications of DL in real life. Physics-guided deep learning (PGDL) is a novel type of DL that can integrate physics laws to train neural networks. It can be used for any systems that are controlled or governed by physics laws, such as mechanics, finance and medical applications. It has been shown that, with the additional information provided by physics laws, PGDL achieves great accuracy and generalisation when facing data scarcity. In this review, the details of PGDL are elucidated, and a structured overview of PGDL with respect to data scarcity in various applications is presented, including physics, engineering and medical applications. Moreover, the limitations and opportunities for current PGDL in terms of data scarcity are identified, and the future outlook for PGDL is discussed in depth.
Generative models such as generative adversarial networks and autoencoders have gained a great deal of attention in the medical field due to their excellent data generation capability. This paper provides a comprehensive survey of generative models for three-dimensional (3D) volumes, focusing on the brain and heart. A new and elaborate taxonomy of unconditional and conditional generative models is proposed to cover diverse medical tasks for the brain and heart: unconditional synthesis, classification, conditional synthesis, segmentation, denoising, detection, and registration. We provide relevant background, examine each task and also suggest potential future directions. A list of the latest publications will be updated on Github to keep up with the rapid influx of papers at \url{https://github.com/csyanbin/3D-Medical-Generative-Survey}.
In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image pair can be identified without ambiguity. However, the projected pattern significantly alters the appearance of the image. If this pattern acts as a form of adversarial noise, it could negatively impact the performance of deep learning-based methods, which are now the de-facto standard for dense stereo vision. In this paper, we propose the Active-Passive SimStereo dataset and a corresponding benchmark to evaluate the performance gap between passive and active stereo images for stereo matching algorithms. Using the proposed benchmark and an additional ablation study, we show that the feature extraction and matching modules of a selection of twenty selected deep learning-based stereo matching methods generalize to active stereo without a problem. However, the disparity refinement modules of three of the twenty architectures (ACVNet, CascadeStereo, and StereoNet) are negatively affected by the active stereo patterns due to their reliance on the appearance of the input images.
A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision. Active vision systems enable more accurate estimations of dense disparity compared to passive stereo. However, subpixel-accurate disparity estimation remains an open problem that has received little attention. In this paper, we propose a new learning strategy to train neural networks to estimate high-quality subpixel disparity maps for semi-dense active stereo vision. The key insight is that neural networks can double their accuracy if they are able to jointly learn how to refine the disparity map while invalidating the pixels where there is insufficient information to correct the disparity estimate. Our approach is based on Bayesian modeling where validated and invalidated pixels are defined by their stochastic properties, allowing the model to learn how to choose by itself which pixels are worth its attention. Using active stereo datasets such as Active-Passive SimStereo, we demonstrate that the proposed method outperforms the current state-of-the-art active stereo models. We also demonstrate that the proposed approach compares favorably with state-of-the-art passive stereo models on the Middlebury dataset.
The generation of three-dimensional (3D) medical images can have great application potential since it takes into account the 3D anatomical structure. There are two problems, however, that prevent effective training of a 3D medical generative model: (1) 3D medical images are very expensive to acquire and annotate, resulting in an insufficient number of training images, (2) a large number of parameters are involved in 3D convolution. To address both problems, we propose a novel GAN model called 3D Split&Shuffle-GAN. In order to address the 3D data scarcity issue, we first pre-train a two-dimensional (2D) GAN model using abundant image slices and inflate the 2D convolution weights to improve initialization of the 3D GAN. Novel 3D network architectures are proposed for both the generator and discriminator of the GAN model to significantly reduce the number of parameters while maintaining the quality of image generation. A number of weight inflation strategies and parameter-efficient 3D architectures are investigated. Experiments on both heart (Stanford AIMI Coronary Calcium) and brain (Alzheimer's Disease Neuroimaging Initiative) datasets demonstrate that the proposed approach leads to improved 3D images generation quality with significantly fewer parameters.
Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided.