Search Results for author:
Found 8 papers, 4 papers with code
Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation
Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances.
SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
Specifically, we leverage the class prototypes that carry positive shared features and propose a Multi-Scaled Distribution-Weighted (MSDW) consistency loss for narrowing the gap between the CAMs generated through classifier weights and class prototypes during training.
Modeling Multi-aspect Preferences and Intents for Multi-behavioral Sequential Recommendation
To extract multi-aspect preferences from target behaviors, we propose a multi-aspect projection mechanism for generating multiple preference representations from multiple aspects.
DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation
The GLSA has the ability to aggregate and represent both global and local spatial features, which are beneficial for locating large and small objects, respectively.
Ranked #1 on
Medical Image Segmentation
on 2018 Data Science Bowl
Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis
An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed.
Deep Meta-learning in Recommendation Systems: A Survey
For each recommendation scenario, we further discuss technical details about how existing methods apply meta-learning to improve the generalization ability of recommendation models.
Stepwise Feature Fusion: Local Guides Global
However, due to the structure of polyps image and the varying shapes of polyps, it easy for existing deep learning models to overfitting the current dataset.
Ranked #2 on
Medical Image Segmentation
on 2018 Data Science Bowl
Jointly Modeling Heterogeneous Student Behaviors and Interactions Among Multiple Prediction Tasks
In this paper, we focus on modeling heterogeneous behaviors and making multiple predictions together, since some prediction tasks are related and learning the model for a specific task may have the data sparsity problem.
