Model-based diagnosis (MBD) with multiple abnormal observations poses a significant challenge. To address this, we propose the Dual Principles with Decision Node (DPDN) algorithm. DPDN encompasses two novel principles...
详细信息
The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguati...
详细信息
Drivable area or free space detection is an essential part of the perception system of an autonomous vehicle. It helps intelligent vehicles understand road conditions and determine safe driving areas. Most of the driv...
详细信息
Medical image registration is a fundamental and critical task in medical image analysis. With the rapid development of deep learning, convolutional neural networks (CNN) have dominated the medical image registration f...
详细信息
Semi-supervised node classification is a task of predicting the labels of unlabeled nodes using limited labeled nodes and numerous unlabeled nodes. Recently, Graph Neural Networks (GNNs) have achieved remarkable succe...
详细信息
Due to the fact that the locations of base stations (BSs) cannot be changed after they are installed, it is very difficult to communicate directly with remote user equipment (UE), which will directly affect the lifesp...
详细信息
Wireless rechargeable sensor networks with a charging unmanned aerial vehicle (CUAV) have the broad application prospects in the power supply of the rechargeable sensor nodes (SNs). However, how to schedule a CUAV and...
详细信息
The detection of drivable areas holds immense significance within the perception system of autonomous vehicles. This capability enables intelligent vehicles to gain a comprehensive understanding of the current road co...
The detection of drivable areas holds immense significance within the perception system of autonomous vehicles. This capability enables intelligent vehicles to gain a comprehensive understanding of the current road conditions and effectively identify safe areas suitable for safe navigation. Convolutional Neural Networks (CNNs) have achieved significant progress in the application of drivable areas detection, particularly in semantic segmentation. However, most existing CNN-based methods for drivable area detection only consider information within a local neighborhood, thus failing to effectively capture long-range dependencies. To tackle this concern, we propose a novel U-shaped network based on the Swin Transformer. The Swin Transformer block was employed as the fundamental element of both the encoder and decoder. Additionally, an upsampling layer was introduced in the decoder to effectively restore the resolution of the feature map. We evaluate our approach on the Cityscapes dataset, a publicly available benchmark for autonomous driving. Experimental results verify the exceptional performance of our proposed method, achieving an impressive mean Intersection over Union (mIoU) score of 91.61%. Our method outperforms existing state-of-the-art techniques in road segmentation detection, further demonstrating its superiority.
Drug-Drug Interaction (DDI) prediction task is helpful for better-understanding drugs. In this paper, we propose a novel drug-drug interaction prediction model based on line subgraph generation strategy, named DDI-LSG...
详细信息
This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the ...
详细信息
This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)
暂无评论