5 papers
Sculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learning
Liang Bai, Hong Song, Jinfu Li +6
Real-world applications often face data privacy constraints and high acquisition costs, making the assumption of sufficient training data in incremental tasks unrealistic and leadi…
GMOR: A Lightweight Robust Point Cloud Registration Framework via Geometric Maximum Overlapping
Zhao Zheng, Jingfan Fan, Long Shao +6
Point cloud registration based on correspondences computes the rigid transformation that maximizes the number of inliers constrained within the noise threshold. Current state-of-th…
MoCTEFuse: Illumination-Gated Mixture of Chiral Transformer Experts for Multi-Level Infrared and Visible Image Fusion
Li Jinfu, Song Hong, Xia Jianghan +5
While illumination changes inevitably affect the quality of infrared and visible image fusion, many outstanding methods still ignore this factor and directly merge the information…
MetaFE-DE: Learning Meta Feature Embedding for Depth Estimation from Monocular Endoscopic Images
Dawei Lu, Deqiang Xiao, Danni Ai +7
Depth estimation from monocular endoscopic images presents significant challenges due to the complexity of endoscopic surgery, such as irregular shapes of human soft tissues, as we…
Efficient Non-Exemplar Class-Incremental Learning with Retrospective Feature Synthesis
Liang Bai, Hong Song, Yucong Lin +5
Despite the outstanding performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning from continuous data streams in real-world scen…