Biosignal representation learning (BRL) plays a crucial role in emotion recognition for game users (ERGU). Unsupervised BRL has garnered attention considering the difficulty in obtaining ground truth emotion labels fr...
详细信息
Biosignal representation learning (BRL) plays a crucial role in emotion recognition for game users (ERGU). Unsupervised BRL has garnered attention considering the difficulty in obtaining ground truth emotion labels from game users. However, unsupervised BRL in ERGU faces challenges, including overfitting caused by limited data and performance degradation due to unbalanced sample distributions. Faced with the above challenges, we propose a novel method of biosignal contrastive representation learning (BCRL) for ERGU, which not only serves as a unified representation learning approach applicable to various modalities of biosignals but also derives generalized biosignals representations suitable for different downstream tasks. Specifically, we solve the overfitting by introducing perturbations at the embedding layer based on the projected gradient descent (PGD) adversarial attacks and develop the sample balancing strategy (SBS) to mitigate the negative impact of the unbalanced sample on the performance. Further, we have conducted comprehensive validation experiments on the public dataset, yielding the following key observations: 1) BCRL outperforms all other methods, achieving average accuracies of 76.67%, 71.83%, and 63.58% in 1D-2C Valence, 1D-2C Arousal and 2D-4C Valence/Arousal, respectively;2) The ablation study shows that both the PGD module (+7.58% in accuracy on average) and the SBS module (+14.60% in accuracy on average) have a positive effect on the performance of different classifications;3) BCRL model exhibits the certain generalization ability across the different games, subjects and classifiers. IEEE
Knowledge distillation(KD) enhances student network generalization by transferring dark knowledge from a complex teacher network. To optimize computational expenditure and memory utilization, self-knowledge distillati...
详细信息
Knowledge distillation(KD) enhances student network generalization by transferring dark knowledge from a complex teacher network. To optimize computational expenditure and memory utilization, self-knowledge distillation(SKD) extracts dark knowledge from the model itself rather than an external teacher network. However, previous SKD methods performed distillation indiscriminately on full datasets, overlooking the analysis of representative samples. In this work, we present a novel two-stage approach to providing targeted knowledge on specific samples, named two-stage approach self-knowledge distillation(TOAST). We first soften the hard targets using class medoids generated based on logit vectors per class. Then, we iteratively distill the under-trained data with past predictions of half the batch size. The two-stage knowledge is linearly combined, efficiently enhancing model performance. Extensive experiments conducted on five backbone architectures show our method is model-agnostic and achieves the best generalization ***, TOAST is strongly compatible with existing augmentation-based regularization methods. Our method also obtains a speedup of up to 2.95x compared with a recent state-of-the-art method.
We study embeddings of the n-dimensional hypercube into the circuit with *** prove that the circular wirelength attains a minimum by gray coding;that was called the CT conjecture by Chavez and Trapp(Discrete Applied M...
详细信息
We study embeddings of the n-dimensional hypercube into the circuit with *** prove that the circular wirelength attains a minimum by gray coding;that was called the CT conjecture by Chavez and Trapp(Discrete Applied Mathematics,1998).This problem had claimed to be settled by Ching-Jung Guu in her doctoral dissertation“The circular wirelength problem for hypercubes”(University of California,Riverside,1997).Many argue there are gaps in her *** eliminate the gaps in her dissertation.
Recently, neural network-based in-loop filters have been rapidly developed, effectively improving the reconstruction quality and compression efficiency in video coding. Existing deep in-loop filters typically employed...
详细信息
We consider the online convex optimization (OCO) problem with quadratic and linear switching cost when at time t only gradient information for functions fτ, τ 16(Lµ+5) for the quadratic switching cost, and also...
详细信息
We consider the online convex optimization (OCO) problem with quadratic and linear switching cost when at time t only gradient information for functions fτ, τ 16(Lµ+5) for the quadratic switching cost, and also show the bound to be order-wise tight in terms of L, µ. In addition, we show that the competitive ratio of any online algorithm is at least max{Ω(L), Ω(pLµ )} when the switching cost is quadratic. For the linear switching cost, the competitive ratio of the OMGD algorithm is shown to depend on both the path length and the squared path length of the problem instance, in addition to L, µ, and is shown to be order-wise, the best competitive ratio any online algorithm can achieve. Copyright is held by author/owner(s).
Federated Adversarial Learning (FAL) maintains the decentralization of adversarial training for data-driven innovations while allowing the collaborative training of a common model to protect privacy facilities. Before...
详细信息
Parkinson's disease (PD) diagnosis involves the assessment of a variety of motor and non-motor symptoms. To accurately diagnose PD, it is necessary to differentiate its symptoms from those of other conditions. Dur...
详细信息
Efficient operations in distributed environments can be obtained by load balancing (LB). LB has turned out to be a vital and interesting research area with respect to the cloud owing to the swift augmentation of cloud...
详细信息
Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distorti...
详细信息
Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distortion. However, current technologies have barely explored the correlation between perturbation removal and background restoration, consequently struggling to generate high-naturalness content in challenging scenarios. In this paper, we rethink the image enhancement task from the perspective of joint optimization: Perturbation removal and texture reconstruction. To this end, we advise an efficient yet effective image enhancement model, termed the perturbation-guided texture reconstruction network(PerTeRNet). It contains two subnetworks designed for the perturbation elimination and texture reconstruction tasks, respectively. To facilitate texture recovery,we develop a novel perturbation-guided texture enhancement module(PerTEM) to connect these two tasks, where informative background features are extracted from the input with the guidance of predicted perturbation priors. To alleviate the learning burden and computational cost, we suggest performing perturbation removal in a sub-space and exploiting super-resolution to infer high-frequency background details. Our PerTeRNet has demonstrated significant superiority over typical methods in both quantitative and qualitative measures, as evidenced by extensive experimental results on popular image enhancement and joint detection tasks. The source code is available at https://***/kuijiang94/PerTeRNet.
Internet of Vehicles (IoV) integrates with various heterogeneous nodes, such as connected vehicles, roadside units, etc., which establishes a distributed network. Vehicles are managed nodes providing all the services ...
详细信息
暂无评论