Search Results for author:
Found 6 papers, 4 papers with code
Towards a General Framework for Continual Learning with Pre-training
In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artificial intelligence systems to accommodate real-world dynamics.
Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
Following these empirical and theoretical insights, we propose Hierarchical Decomposition (HiDe-)Prompt, an innovative approach that explicitly optimizes the hierarchical components with an ensemble of task-specific prompts and statistics of both uninstructed and instructed representations, further with the coordination of a contrastive regularization strategy.
Knowledge-Enhanced Hierarchical Information Correlation Learning for Multi-Modal Rumor Detection
The explosive growth of rumors with text and images on social media platforms has drawn great attention.
Label Noise-Resistant Mean Teaching for Weakly Supervised Fake News Detection
LNMT leverages unlabeled news and feedback comments of users to enlarge the amount of training data and facilitates model training by generating refined labels as weak supervision.
SegFix: Model-Agnostic Boundary Refinement for Segmentation
We present a model-agnostic post-processing scheme to improve the boundary quality for the segmentation result that is generated by any existing segmentation model.
ABD-Net: Attentive but Diverse Person Re-Identification
Attention mechanism has been shown to be effective for person re-identification (Re-ID).
Ranked #16 on
Person Re-Identification
on Market-1501-C
