activity
20242026
most citedA Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective

7 citations · 12 across the 26 of their papers we have counts for

collaborators
Showing 2024Show all

9 papers · 1 filter

cs.CV2024

Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning

Ran Ma, Yixiong Zou, Yuhua Li +1

Cross-Domain Few-Shot Learning (CDFSL) requires the model to transfer knowledge from the data-abundant source domain to data-scarce target domains for fast adaptation, where the la…

cs.CV2024★ 2 cited

Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation

Jintao Tong, Yixiong Zou, Yuhua Li +1

Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset, and then transfer the model to data-scarce target-domai…

cs.CV2024★ 1 cited

MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning

Zhenyu Zhang, Guangyao Chen, Yixiong Zou +3

Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems. Un…

cs.CV2024

Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition

Zhenyu Zhang, Guangyao Chen, Yixiong Zou +2

Few-shot open-set recognition (FSOR) is a challenging task that requires a model to recognize known classes and identify unknown classes with limited labeled data. Existing approac…

cs.CV2024

Compositional Few-Shot Class-Incremental Learning

Yixiong Zou, Shanghang Zhang, Haichen Zhou +2

Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient dat…

cs.CV2024

Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning

Haichen Zhou, Yixiong Zou, Ruixuan Li +2

Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods addre…