Learning from Reduced Labels for Long-Tailed Data

arXiv:2403.16469v1 Announce Type: new
Abstract: Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common approach to mitigate labeling costs, existing weakly supervised learning methods struggle to adequately preserve supervised information for tail samples, resulting in a decline in accuracy for the tail classes. To alleviate this problem, we introduce a novel weakly supervised labeling setting called Reduced Label. The proposed labeling …

abstract annotation arxiv classification costs cs.cv cs.lg data information labeling labels labor process samples struggle supervised learning tasks type world