Papers › Probability Guided Loss for Long-Tailed Multi-Label Image Classification

Probability Guided Loss for Long-Tailed Multi-Label Image Classification

26 Jun 2023AAAI 2023 6archive 2025-07-28

Dekun Lin

Long-tailed learning has attracted increasing attention in very recent years. Long-tailed multi-label image classification is one subtask and remains challenging and poorly researched. In this paper, we provide a fresh perspective from probability to tackle this problem. More specifically, we find that existing cost-sensitive learning methods for long-tailed multi-label classification will affect the predicted probability of positive and negative labels in varying degrees during training, and different processes of probability will affect the final performance in turn. We thus propose a probability guided loss which contains two components to control this process. One is the probability re-balancing which can flexibly adjust the process of training probability. And the other is the adaptive probability-aware focal which can further reduce the probability gap between positive and negative labels. We conduct extensive experiments on two long-tailed multi-label image classification datasets: VOC-LT and COCO-LT. The results demonstrate the rationality and superiority of our strategy.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationImage ClassificationLong-tail LearningMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationMulti-Label Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning COCO-MLT PG Loss(ResNet-50) Average mAP 54.43 #6 of 13 Archive leaderboard report
Long-tail Learning VOC-MLT PG Loss(ResNet-50) Average mAP 80.37 #6 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections