When visual image information is transmitted via communication networks, it easily suffers from image attacks, leading to system performance degradation or even crash. This paper investigates secure control of networked inverted pendulum visual servo system (NIPVSS) with adverse effects of image computation. Firstly, the image security limitation of the traditional NIPVSS is revealed, where its stability will be destroyed by eavesdropping-based image attacks. Then, a new NIPVSS with the fast scaled-selective image encryption (F2SIE) algorithm is proposed, which not only meets the real-time requirement by reducing the computational complexity, but also improve the security by reducing the probability of valuable information being compromised by eavesdropping-based image attacks. Secondly, adverse effects of the F2SIE algorithm and image attacks are analysed, which will produce extra computational delay and errors. Then, a closed-loop uncertain time-delay model of the new NIPVSS is established, and a robust controller is designed to guarantee system asymptotic stability. Finally, experimental results of the new NIPVSS demonstrate the feasibility and effectiveness of the proposed method.
Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones, etc. Most existing pFL methods focus on exploiting the global information and personalized information in the client-level model parameters while neglecting that data is the source of these two kinds of information. To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively. FedCP is more fine-grained to consider personalization in a sample-specific manner than existing pFL methods. Extensive experiments in computer vision and natural language processing domains show that FedCP outperforms eleven state-of-the-art methods by up to 6.69%. Furthermore, FedCP maintains its superiority when some clients accidentally drop out, which frequently happens in mobile settings. Our code is public at https://github.com/TsingZ0/FedCP.
Blinding eye diseases are often correlated with altered retinal morphology, which can be clinically identified by segmenting retinal structures in fundus images. However, current methodologies often fall short in accurately segmenting delicate vessels. Although deep learning has shown promise in medical image segmentation, its reliance on repeated convolution and pooling operations can hinder the representation of edge information, ultimately limiting overall segmentation accuracy. In this paper, we propose a lightweight pixel-level CNN named LMBiS-Net for the segmentation of retinal vessels with an exceptionally low number of learnable parameters \textbf{(only 0.172 M)}. The network used multipath feature extraction blocks and incorporates bidirectional skip connections for the information flow between the encoder and decoder. Additionally, we have optimized the efficiency of the model by carefully selecting the number of filters to avoid filter overlap. This optimization significantly reduces training time and enhances computational efficiency. To assess the robustness and generalizability of LMBiS-Net, we performed comprehensive evaluations on various aspects of retinal images. Specifically, the model was subjected to rigorous tests to accurately segment retinal vessels, which play a vital role in ophthalmological diagnosis and treatment. By focusing on the retinal blood vessels, we were able to thoroughly analyze the performance and effectiveness of the LMBiS-Net model. The results of our tests demonstrate that LMBiS-Net is not only robust and generalizable but also capable of maintaining high levels of segmentation accuracy. These characteristics highlight the potential of LMBiS-Net as an efficient tool for high-speed and accurate segmentation of retinal images in various clinical applications.
Since annotating medical images for segmentation tasks commonly incurs expensive costs, it is highly desirable to design an annotation-efficient method to alleviate the annotation burden. Recently, contrastive learning has exhibited a great potential in learning robust representations to boost downstream tasks with limited labels. In medical imaging scenarios, ready-made meta labels (i.e., specific attribute information of medical images) inherently reveal semantic relationships among images, which have been used to define positive pairs in previous work. However, the multi-perspective semantics revealed by various meta labels are usually incompatible and can incur intractable "semantic contradiction" when combining different meta labels. In this paper, we tackle the issue of "semantic contradiction" in a gradient-guided manner using our proposed Gradient Mitigator method, which systematically unifies multi-perspective meta labels to enable a pre-trained model to attain a better high-level semantic recognition ability. Moreover, we emphasize that the fine-grained discrimination ability is vital for segmentation-oriented pre-training, and develop a novel method called Gradient Filter to dynamically screen pixel pairs with the most discriminating power based on the magnitude of gradients. Comprehensive experiments on four medical image segmentation datasets verify that our new method GCL: (1) learns informative image representations and considerably boosts segmentation performance with limited labels, and (2) shows promising generalizability on out-of-distribution datasets.
Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders are typically designed to extract generic image-level features that summarize superfluous or confounding information for the target tasks. This results in degradation of classification performance, especially when objects of interest cover small areas of input images. In this work, we propose CLIP with Guided Cropping (GC-CLIP), where we use an off-the-shelf zero-shot object detection model in a preprocessing step to increase focus of zero-shot classifier to the object of interest and minimize influence of extraneous image regions. We empirically show that our approach improves zero-shot classification results across architectures and datasets, favorably for small objects.
Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning. However, the existing Hierarchical Reinforcement Learning (HRL) approaches relying on symbolic reasoning are often limited as they require a manual goal representation. The challenge in autonomously discovering a symbolic goal representation is that it must preserve critical information, such as the environment dynamics. In this work, we propose a developmental mechanism for subgoal discovery via an emergent representation that abstracts (i.e., groups together) sets of environment states that have similar roles in the task. We create a HRL algorithm that gradually learns this representation along with the policies and evaluate it on navigation tasks to show the learned representation is interpretable and results in data efficiency.
Oscillating-gradient spin-echo diffusion-weighted magnetic resonance imaging (OGSE-DWI) has been promoted as a promising technique for studying the microstructure of complex hydrated matter in the frequency domain. The target of the OGSE-DWI technique is the spectral density of molecular diffusion, $u_{2}(\omega)$, which is predicted to obey a set of asymptotic universality relations that are linked to the global organisation of the sample. So, in principle the complex microstructure of a medium can be classified by measuring the spectral density in its low- and high-frequency limits. However, due to practical limitations on the spectral resolution and range of the technique, it is not possible to directly sample the spectral density with OGSE-DWI. Rather, information about the spectral density can be obtained only indirectly through the quantities $U_{kk}$ & $U_{k0}$, which are filtered representations of $u_{2}(\omega)$. The purpose of this study is to investigate how the universal behaviour of $u_{2}(\omega)$ emerges in the asymptotic behaviour of OGSE-DWI signal.
Music genre classification has become increasingly critical with the advent of various streaming applications. Nowadays, we find it impossible to imagine using the artist's name and song title to search for music in a sophisticated music app. It is always difficult to classify music correctly because the information linked to music, such as region, artist, album, or non-album, is so variable. This paper presents a study on music genre classification using a combination of Digital Signal Processing (DSP) and Deep Learning (DL) techniques. A novel algorithm is proposed that utilizes both DSP and DL methods to extract relevant features from audio signals and classify them into various genres. The algorithm was tested on the GTZAN dataset and achieved high accuracy. An end-to-end deployment architecture is also proposed for integration into music-related applications. The performance of the algorithm is analyzed and future directions for improvement are discussed. The proposed DSP and DL-based music genre classification algorithm and deployment architecture demonstrate a promising approach for music genre classification.
Conversational recommender systems (CRS) generate recommendations through an interactive process. However, not all CRS approaches use human conversations as their source of interaction data; the majority of prior CRS work simulates interactions by exchanging entity-level information. As a result, claims of prior CRS work do not generalise to real-world settings where conversations take unexpected turns, or where conversational and intent understanding is not perfect. To tackle this challenge, the research community has started to examine holistic CRS, which are trained using conversational data collected from real-world scenarios. Despite their emergence, such holistic approaches are under-explored. We present a comprehensive survey of holistic CRS methods by summarizing the literature in a structured manner. Our survey recognises holistic CRS approaches as having three components: 1) a backbone language model, the optional use of 2) external knowledge, and/or 3) external guidance. We also give a detailed analysis of CRS datasets and evaluation methods in real application scenarios. We offer our insight as to the current challenges of holistic CRS and possible future trends.
In spite of the excellent strides made by end-to-end (E2E) models in speech recognition in recent years, named entity recognition is still challenging but critical for semantic understanding. In order to enhance the ability to recognize named entities in E2E models, previous studies mainly focus on various rule-based or attention-based contextual biasing algorithms. However, their performance might be sensitive to the biasing weight or degraded by excessive attention to the named entity list, along with a risk of false triggering. Inspired by the success of the class-based language model (LM) in named entity recognition in conventional hybrid systems and the effective decoupling of acoustic and linguistic information in the factorized neural Transducer (FNT), we propose a novel E2E model to incorporate class-based LMs into FNT, which is referred as C-FNT. In C-FNT, the language model score of named entities can be associated with the name class instead of its surface form. The experimental results show that our proposed C-FNT presents significant error reduction in named entities without hurting performance in general word recognition.