Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification
This work addresses label noise issues in multi-label classification for computer vision applications, but it is incremental as it builds on existing baseline methods.
The paper tackles the problem of false negative labels in partially annotated multi-label classification by analyzing their impact on model explanations, finding that partial labels lead to lower attribution scores, and proposes boosting these scores to improve classification performance, achieving large-margin gains in multiple datasets.
Due to the expensive costs of collecting labels in multi-label classification datasets, partially annotated multi-label classification has become an emerging field in computer vision. One baseline approach to this task is to assume unobserved labels as negative labels, but this assumption induces label noise as a form of false negative. To understand the negative impact caused by false negative labels, we study how these labels affect the model's explanation. We observe that the explanation of two models, trained with full and partial labels each, highlights similar regions but with different scaling, where the latter tends to have lower attribution scores. Based on these findings, we propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels. Even with the conceptually simple approach, the multi-label classification performance improves by a large margin in three different datasets on a single positive label setting and one on a large-scale partial label setting. Code is available at https://github.com/youngwk/BridgeGapExplanationPAMC.