Multimodal sentiment analysis aims to predict human sentiment polarity with multiple modalities. Most existing methods focus on directly integrating original modal features into multimodal fusion, ignoring the redunda...
详细信息
Unsupervised graph anomaly detection has been widely used in real-world applications. Existing methods primarily focus on local inconsistency mining (LIM), based on the intuition that establishing high similarities be...
详细信息
Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use...
详细信息
Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement. Copyright 2024 by the author(s)
Biometrics have inherent uniqueness and can provide a higher level of security than traditional methods. Additionally, the use of biometrics reduces the need for users to remember complex passwords or carry physical t...
详细信息
Originally presented in previous work to capture the set of fundamental elements of the UML state machine specification, Common Declarative Language (CDL) provides a model that can aid in the validation and verificati...
详细信息
Recently, post-training quantization (PTQ) has become the de facto way to produce efficient low-precision neural networks without long-time retraining. Despite its low cost, current PTQ works fail to succeed under the...
详细信息
Cryptographic APIs provided by Ethereum are widely adopted in decentralized applications (DApps) for cryptographic operations. However, developers who lack expertise in cryptography frequently encounter difficulties w...
详细信息
With the rapid development of intelligent systems, Multi-Agent Systems (MAS) have shown unique advantages in solving complex decision-making problems. Particularly in the field of Multi-Agent Reinforcement Learning (M...
详细信息
Self-training with data augmentation emerges as an efficacious strategy for harnessing unlabeled data in the realm of semi-supervised medical image segmentation. Within the synthetic domain, existing models make a del...
详细信息
In the past decades, ontology-based query expansion has been studied to improve health and biomedical information retrieval by many researchers, but the results of previous works are inconsistent. Query expansion with...
详细信息
暂无评论