Abstract: Knowledge distillation has demonstrated considerable success in scenarios involving multi-class single-label learning. However, its direct application to multi-label learning proves ...
Abstract: While single-label class incremental learning (CIL) has seen significant progress, multi-label class incremental learning (MLCIL) remains relatively unexplored. In MLCIL, newly introduced ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results