Titlebook: Artificial Intelligence; Third CAAI Internati Lu Fang,Jian Pei,Ruiping Wang Conference proceedings 2024 The Editor(s) (if applicable) and T

原來(lái)

Interferons

FairDR: Ensuring Fairness in?Mixed Data of?Fairly and?Unfairly Treated Instancescausal structures. Leveraging the perspective of SCM, we propose a framework called FairDR, which utilizes the Hirschfeld-Gebelein-Rényi (HGR) correlation to accurately recover the distribution of both fairly and unfairly treated data. FairDR can serve as a pre-processing method for other fair machi

啞劇

Blind Adversarial Training: Towards Comprehensively Robust Models Against Blind Adversarial Attacks estimate a nonuniform budget to modify the AEs used in training, ensuring that the strengths of the AEs are dynamically located in a reasonable range and ultimately improving the comprehensive robustness of the AT model. We include a theoretical investigation on a toy classification problem to guar

清唱?jiǎng)?/a>

atrophy

AIGCIQA2023: A Large-Scale Image Quality Assessment Database for?AI Generated Images: From the?Perspassess the human visual preferences for each image from three perspectives including ., . and .. Finally, based on this large-scale database, we conduct a benchmark experiment to evaluate the performance of several state-of-the-art IQA metrics on our constructed database. The AIGCIQA2023 database an

BOAST

Pulmonary-Veins

Domain Specific Pre-training Methods for?Traditional Chinese Medicine Prescription Recommendationnd multi-grained negative sampling methods and training objectives. To verify the effectiveness of the proposed method, we conduct extensive experiments on the symptom-prescription dataset. The experiment results show that our proposed method can accurately recommend suitable prescriptions with more

背書(shū)

LTUNet: A Lightweight Transformer-Based UNet with?Multi-scale Mechanism for?Skin Lesion Segmentationres are used to enhance the feature map of each scale. Finally, we fuse the upsampled results of all scales on UNet to improve the performance of segmentation. Our method achieves 0.9432, 0.8948, 0.9348 for mDice, mIoU and mACC on the ISIC2016 dataset, and 0.9058, 0.8138, 0.8968 on the ISIC2018 data

免費(fèi)

A Novel Online Multi-label Feature Selection Approach for?Multi-dimensional Streaming Data we recalculates the weights of all current labels and updates the total Fisher score to update the current feature rank list. In the experiments, we compare the performance of our approach with four representative online feature selection algorithms for streaming features and labels, respectively.

錯(cuò)事

M,Sim: A Long-Term Interactive Driving Simulatorediction model M2I, forming a new simulator named M.Sim. Notably, M.Sim can effectively address the OOD problem of long-term simulation by enforcing a flexible regularization that admits the replayed data, while still enjoying the diversity of data-driven predictions. We demonstrate the superiority