Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance b...
详细信息
Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.
In recent years, deep learning has significantly advanced skin lesion segmentation. However, annotating medical image data is specialized and costly, while obtaining unlabeled medical data is easier. To address this c...
详细信息
Detecting dangerous driving behavior is a critical research area focused on identifying and preventing actions that could lead to traffic accidents, such as smoking, drinking, yawning, and drowsiness, through technica...
详细信息
Image captioning is an interdisciplinary research hotspot at the intersection of computer vision and natural language processing, representing a multimodal task that integrates core technologies from both fields. This...
详细信息
With the development of artificial intelligence, deep learning has been increasingly used to achieve automatic detection of geographic information, replacing manual interpretation and improving efficiency. However, re...
详细信息
With the development of deep learning in recent years, code representation learning techniques have become the foundation of many softwareengineering tasks such as program classification [1] and defect detection. Ear...
With the development of deep learning in recent years, code representation learning techniques have become the foundation of many softwareengineering tasks such as program classification [1] and defect detection. Earlier approaches treat the code as token sequences and use CNN, RNN, and the Transformer models to learn code representations.
Concrete is a vital component in modern construction, prized for its strength, durability, and versatility. Accurately determining the quantities of concrete components is crucial in civil engineering applications to ...
详细信息
GPT is widely recognized as one of the most versatile and powerful large language models, excelling across diverse domains. However, its significant computational demands often render it economically unfeasible for in...
详细信息
Dear Editor,This letter presents a new transfer learning framework for the deep multi-agent reinforcement learning(DMARL) to reduce the convergence difficulty and training time when applying DMARL to a new scenario [1...
详细信息
Dear Editor,This letter presents a new transfer learning framework for the deep multi-agent reinforcement learning(DMARL) to reduce the convergence difficulty and training time when applying DMARL to a new scenario [1], [2].
In this paper,we tackle the challenging problem of point cloud completion from the perspective of feature *** key observation is that to recover the underlying structures as well as surface details,given partial input...
详细信息
In this paper,we tackle the challenging problem of point cloud completion from the perspective of feature *** key observation is that to recover the underlying structures as well as surface details,given partial input,a fundamental component is a good feature representation that can capture both global structure and local geometric *** accordingly first propose FSNet,a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map by learning multiple latent patterns from local *** then integrate FSNet into a coarse-to-fine pipeline for point cloud ***,a 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point ***,a point cloud upsampling network is used to generate a dense point cloud from the partial input and the coarse intermediate *** efficiently exploit local structures and enhance point distribution uniformity,we propose IFNet,a point upsampling module with a self-correction mechanism that can progressively refine details of the generated dense point *** have conducted qualitative and quantitative experiments on ShapeNet,MVP,and KITTI datasets,which demonstrate that our method outperforms stateof-the-art point cloud completion approaches.
暂无评论