Logic synthesis is a crucial step in integrated circuit design, and area optimization is an indispensable part of this process. However, the area optimization problem for large-scale Fixed Polarity Reed-Muller (FPRM) ...
详细信息
The integration of psychology and computer science has become the mainstream contemporary research method on psychological data. Weibo, China's largest open platform for communication and information sharing betwe...
详细信息
Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge ...
Image segmentation is a crucial task in the field of computer vision. Markov random fields (MRF) based image segmentation method can effectively capture intricate relationships among pixels. However, MRF typically req...
详细信息
There are a wide variety of intelligence accelerators with promising performance and energy efficiency,deployed in a broad range of applications such as computer vision and speech ***,programming productivity hinders ...
详细信息
There are a wide variety of intelligence accelerators with promising performance and energy efficiency,deployed in a broad range of applications such as computer vision and speech ***,programming productivity hinders the deployment of deep learning *** low-level library invoked in the high-level deep learning framework which supports the end-to-end execution with a given model,is designed to reduce the programming burden on the intelligence ***,it is inflexible for developers to build a network model for every deep learning application,which probably brings unnecessary repetitive *** this paper,a flexible and efficient programming framework for deep learning accelerators,FlexPDA,is proposed,which provides more optimization opportunities than the low-level library and realizes quick transplantation of applications to intelligence accelerators for fast *** evaluate FlexPDA by using 10 representative operators selected from deep learning algorithms and an end-to-end *** experimental results validate the effectiveness of FlexPDA,which achieves an end-to-end performance improvement of 1.620x over the low-level library.
Skeleton-based action recognition is crucial for machine intelligence. Current methods generally learn from 3D articulated motion sequences in the straightforward Euclidean space. Yet, the vanilla Euclidean space may ...
详细信息
Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective i...
详细信息
Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.
Transformer-based models are dominating the field of natural language processing and are becoming increasingly popular in the field of computer vision. However, the black box characteristics of transformers seriously ...
详细信息
Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning ...
详细信息
Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or n...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or noisy skeleton data. State-of-the-art methods tend to learn human motion directly from these corrupted skeletons as if they were reliable. Unfortunately, this might lead to unsatisfactory results when key regions of the skeleton are occluded or disturbed. To tackle the problem, we propose a novel framework that integrates auxiliary tasks into a motion modeling network. These auxiliary tasks corrupt partial human skeletons with masking or noise and then force the network to recover the corrupted data, explicitly facilitating robust feature representation learning. We further propose supervising the auxiliary tasks with mutual information losses, mathematically ensuring feature consistency and spatial alignment between the recovered and original skeleton data. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets.
暂无评论