As it is empirically observed that Vision Transformers (ViTs) are quite
...
Domain generalization (DG) attempts to generalize a model trained on sin...
The Class Incremental Semantic Segmentation (CISS) extends the tradition...
The crux of label-efficient semantic segmentation is to produce high-qua...
Domain adaptive semantic segmentation aims to transfer knowledge from a
...
Generalized linear models (GLMs) form one of the most popular classes of...
Masked image modeling (MIM) has attracted much research attention due to...
Few-Shot transfer learning has become a major focus of research as it al...
Collecting and annotating task-oriented dialog data is difficult, especi...
Sound source localization in visual scenes aims to localize objects emit...
Benefited from considerable pixel-level annotations collected from a spe...
Single-pixel cameras based on the concepts of compressed sensing (CS)
le...