4 papers · 1 filter
HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
Eunju Lee, MiHyeon Kim, JuneHyoung Kwon +4
Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains a…
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +2
Vision-language (VL) models have demonstrated strong performance across various tasks. However, these models often rely on a specific modality for predictions, leading to "dominant…
DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation
Soojin Jang, Jungmin Yun, Junehyoung Kwon +2
Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due…
Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
JuneHyoung Kwon, Eunju Lee, Yunsung Cho +1
Weakly supervised semantic segmentation (WSSS) employing weak forms of labels has been actively studied to alleviate the annotation cost of acquiring pixel-level labels. However, c…