67 citations · 330 across the 26 of their papers we have counts for
4 papers · 1 filter
Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition
Xiyao Liu, Zhong Ji, Yanwei Pang +1
The domain shift between the source and target domain is the main challenge in Cross-Domain Few-Shot Learning (CD-FSL). However, the target domain is absolutely unknown during the…
Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning
Zhong Ji, Zhishen Hou, Xiyao Liu +2
Semantic information provides intra-class consistency and inter-class discriminability beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve further…
Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision
Zhong Ji, Jin Li, Qiang Wang +1
General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on t…
Step-Wise Hierarchical Alignment Network for Image-Text Matching
Zhong Ji, Kexin Chen, Haoran Wang
Image-text matching plays a central role in bridging the semantic gap between vision and language. The key point to achieve precise visual-semantic alignment lies in capturing the…