Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels. (arXiv:2304.10539v1 [cs.LG])

Conventional multi-label classification (MLC) methods assume that all samples
are fully labeled and identically distributed. Unfortunately, this assumption
is unrealistic in large-scale MLC data that has long-tailed (LT) distribution
and partial labels (PL). To address the problem, we introduce a novel task,
Partial labeling and Long-Tailed Multi-Label Classification (PLT-MLC), to
jointly consider the above two imperfect learning environments. Not
surprisingly, we find that most LT-MLC and PL-MLC approaches fail to solve the
PLT-MLC, resulting in significant performance degradation on the …

arxiv benchmarks classification data distributed distribution environment environments labeling labels mlc novel performance scale