Y. Lyu

collaborators

3 papers

cs.CV2026

Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning

Haichen Zhou, Yazhe Lyu, Yixiong Zou +2

Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes with only a few samples while avoiding forgetting base classes. However, current methods show…

hep-ex2026

Observation of the Exotic State $I ¨ _{1} (1600)$ in $I ¨ (2 S) \to I^^{3} I ¨ _{c 1}, I ¨ _{c 1} \to I ¨ ^{+} I ¨ ^{-} I^\cdot^{'}$

BESIII Collaboration, M. Ablikim, M. N. Achasov +750

A partial wave analysis of the process $I ¨ (2 S) \to I^^{3} I ¨ _{c 1}, I ¨ _{c 1} \to I ¨ ^{+} I ¨ ^{-} I^\cdot^{'}$ is performed using $(2712.4 \pm 14.3) \times 1 0^{6}$ $I ¨ (2 S)$ events collecte…

cs.CV2026

The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

Xingyu Qiu, Yuqian Fu, Jiawei Geng +70

Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across…

Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning

Observation of the Exotic State I¨1​(1600) in I¨(2S)→I^3I¨c1​,I¨c1​→I¨+I¨−I^⋅′

The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

Observation of the Exotic State $I ¨ _{1} (1600)$ in $I ¨ (2 S) \to I^^{3} I ¨ _{c 1}, I ¨ _{c 1} \to I ¨ ^{+} I ¨ ^{-} I^\cdot^{'}$