2

Mitigating Class Confusion in Class-Incremental Semantic Segmentation
Class-incremental semantic segmentation (CSS) aims to continuously classify every pixel in an image to its corresponding semantic …
Nayoung Ko, Gyeong-hyeon Kim, Eunwoo Kim
PDF Cite DOI
Mitigating Class Confusion in Class-Incremental Semantic Segmentation
GhostNeXt: Rethinking Module Configurations for Efficient Model Design
Despite the continuous development of convolutional neural networks, it remains a challenge to achieve performance improvement with …
Kiseong Hong, Gyeong-hyeon Kim, Eunwoo Kim
PDF Cite DOI
GhostNeXt: Rethinking Module Configurations for Efficient Model Design
Stacked Encoder–Decoder Transformer with Boundary Smoothing for Action Segmentation
In this work, a new stacked encoder–decoder transformer (SEDT) model is proposed for action segmentation. SEDT is composed of a series …
Gyeong-hyeon Kim, Eunwoo Kim
PDF Cite DOI
Stacked Encoder–Decoder Transformer with Boundary Smoothing for Action Segmentation