亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from under-activation of target object regions and false-activation of background regions due to the fact that a lack of detailed supervision can hinder the model's ability to understand the image as a whole. In this paper, we propose a novel Question-Answer Cross-Language-Image Matching framework for WSSS (QA-CLIMS), leveraging the vision-language foundation model to maximize the text-based understanding of images and guide the generation of activation maps. First, a series of carefully designed questions are posed to the VQA (Visual Question Answering) model with Question-Answer Prompt Engineering (QAPE) to generate a corpus of both foreground target objects and backgrounds that are adaptive to query images. We then employ contrastive learning in a Region Image Text Contrastive (RITC) network to compare the obtained foreground and background regions with the generated corpus. Our approach exploits the rich textual information from the open vocabulary as additional supervision, enabling the model to generate high-quality CAMs with a more complete object region and reduce false-activation of background regions. We conduct extensive analysis to validate the proposed method and show that our approach performs state-of-the-art on both PASCAL VOC 2012 and MS COCO datasets. Code is available at: //github.com/CVI-SZU/QA-CLIMS

Medical visual question answering (VQA) is a challenging multimodal task, where Vision-Language Pre-training (VLP) models can effectively improve the generalization performance. However, most methods in the medical field treat VQA as an answer classification task which is difficult to transfer to practical application scenarios. Additionally, due to the privacy of medical images and the expensive annotation process, large-scale medical image-text pairs datasets for pretraining are severely lacking. In this paper, we propose a large-scale MultI-task Self-Supervised learning based framework (MISS) for medical VQA tasks. Unlike existing methods, we treat medical VQA as a generative task. We unify the text encoder and multimodal encoder and align image-text features through multi-task learning. Furthermore, we propose a Transfer-and-Caption method that extends the feature space of single-modal image datasets using large language models (LLMs), enabling those traditional medical vision field task data to be applied to VLP. Experiments show that our method achieves excellent results with fewer multimodal datasets and demonstrates the advantages of generative VQA models. The code and model weights will be released upon the paper's acceptance.

Modern GPU applications, such as machine learning (ML) frameworks, can only partially utilize beefy GPUs, leading to GPU underutilization in cloud environments. Sharing GPUs across multiple applications from different users can improve resource utilization and consequently cost, energy, and power efficiency. However, GPU sharing creates memory safety concerns because kernels must share a single GPU address space (GPU context). Previous GPU memory protection approaches have limited deployability because they require specialized hardware extensions or access to source code. This is often unavailable in GPU-accelerated libraries heavily utilized by ML frameworks. In this paper, we present G-Safe, a PTX-level bounds checking approach for GPUs that limits GPU kernels of each application to stay within the memory partition allocated to them. G-Safe relies on three mechanisms: (1) It divides the common GPU address space into separate partitions for different applications. (2) It intercepts and checks data transfers, fencing erroneous operations. (3) It instruments all GPU kernels at the PTX level (available in closed GPU libraries) fencing all kernel memory accesses outside application memory bounds. We implement G-Safe as an external, dynamically linked library that can be pre-loaded at application startup time. G-Safe's approach is transparent to applications and can support real-life, complex frameworks, such as Caffe and PyTorch, that issue billions of GPU kernels. Our evaluation shows that the overhead of G-Safe compared to native (unprotected) for such frameworks is between 4\% - 12\% and on average 9\%.

The Healthcare Internet-of-Things (H-IoT), commonly known as Digital Healthcare, is a data-driven infrastructure that highly relies on smart sensing devices (i.e., blood pressure monitors, temperature sensors, etc.) for faster response time, treatments, and diagnosis. However, with the evolving cyber threat landscape, IoT devices have become more vulnerable to the broader risk surface (e.g., risks associated with generative AI, 5G-IoT, etc.), which, if exploited, may lead to data breaches, unauthorized access, and lack of command and control and potential harm. This paper reviews the fundamentals of healthcare IoT, its privacy, and data security challenges associated with machine learning and H-IoT devices. The paper further emphasizes the importance of monitoring healthcare IoT layers such as perception, network, cloud, and application. Detecting and responding to anomalies involves various cyber-attacks and protocols such as Wi-Fi 6, Narrowband Internet of Things (NB-IoT), Bluetooth, ZigBee, LoRa, and 5G New Radio (5G NR). A robust authentication mechanism based on machine learning and deep learning techniques is required to protect and mitigate H-IoT devices from increasing cybersecurity vulnerabilities. Hence, in this review paper, security and privacy challenges and risk mitigation strategies for building resilience in H-IoT are explored and reported.

Advancements in large language models (LLMs) are poised to spark a proliferation of LLM-powered user experiences. In product teams, designers are often tasked with crafting user experiences that align with user needs. To involve designers and leverage their user-centered perspectives to create effective and responsible LLM-powered products, we introduce the practice of designerly adaptation for engaging with LLMs as an adaptable design material. We first identify key characteristics of designerly adaptation through a formative study with designers experienced in designing for LLM-powered products (N=12). These characteristics are 1) have a low technical barrier to entry, 2) leverage designers' unique perspectives bridging users and technology, and 3) encourage model tinkering. Based on this characterization, we build Canvil, a Figma widget that operationalizes designerly adaptation. Canvil supports structured authoring of system prompts to adapt LLM behavior, testing of adapted models on diverse user inputs, and integration of model outputs into interface designs. We use Canvil as a technology probe in a group-based design study (6 groups, N=17) to investigate the implications of integrating designerly adaptation into design workflows. We find that designers are able to iteratively tinker with different adaptation approaches and reason about interface affordances to enhance end-user interaction with LLMs. Furthermore, designers identified promising collaborative workflows for designerly adaptation. Our work opens new avenues for collaborative processes and tools that foreground designers' user-centered expertise in the crafting and deployment of LLM-powered user experiences.

With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled. It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data. A major limitation of existing methods has been the focus on grid-like data; however, the structure of physiological recordings are often irregular and unordered which makes it difficult to conceptualise them as a matrix. As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be either temporal associations or anatomical junctions. In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare. We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure and electrical-based analysis. We also outline the limitations of existing techniques and discuss potential directions for future research.

Deep Learning has implemented a wide range of applications and has become increasingly popular in recent years. The goal of multimodal deep learning is to create models that can process and link information using various modalities. Despite the extensive development made for unimodal learning, it still cannot cover all the aspects of human learning. Multimodal learning helps to understand and analyze better when various senses are engaged in the processing of information. This paper focuses on multiple types of modalities, i.e., image, video, text, audio, body gestures, facial expressions, and physiological signals. Detailed analysis of past and current baseline approaches and an in-depth study of recent advancements in multimodal deep learning applications has been provided. A fine-grained taxonomy of various multimodal deep learning applications is proposed, elaborating on different applications in more depth. Architectures and datasets used in these applications are also discussed, along with their evaluation metrics. Last, main issues are highlighted separately for each domain along with their possible future research directions.

Dialogue systems are a popular Natural Language Processing (NLP) task as it is promising in real-life applications. It is also a complicated task since many NLP tasks deserving study are involved. As a result, a multitude of novel works on this task are carried out, and most of them are deep learning-based due to the outstanding performance. In this survey, we mainly focus on the deep learning-based dialogue systems. We comprehensively review state-of-the-art research outcomes in dialogue systems and analyze them from two angles: model type and system type. Specifically, from the angle of model type, we discuss the principles, characteristics, and applications of different models that are widely used in dialogue systems. This will help researchers acquaint these models and see how they are applied in state-of-the-art frameworks, which is rather helpful when designing a new dialogue system. From the angle of system type, we discuss task-oriented and open-domain dialogue systems as two streams of research, providing insight into the hot topics related. Furthermore, we comprehensively review the evaluation methods and datasets for dialogue systems to pave the way for future research. Finally, some possible research trends are identified based on the recent research outcomes. To the best of our knowledge, this survey is the most comprehensive and up-to-date one at present in the area of dialogue systems and dialogue-related tasks, extensively covering the popular frameworks, topics, and datasets.

Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize from few samples, GNN usually suffers from severe over-fitting and over-smoothing as the model becomes deep, which limit the model scalability. In this work, we propose a novel Attentive GNN to tackle these challenges, by incorporating a triple-attention mechanism, \ie node self-attention, neighborhood attention, and layer memory attention. We explain why the proposed attentive modules can improve GNN for few-shot learning with theoretical analysis and illustrations. Extensive experiments show that the proposed Attentive GNN outperforms the state-of-the-art GNN-based methods for few-shot learning over the mini-ImageNet and Tiered-ImageNet datasets, with both inductive and transductive settings.

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.