# Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification

arXiv: https://arxiv.org/abs/2304.01804 · HTML: https://mlsanity.com/paper/2304.01804/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 4 Apr 2023.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.08896/) (2021)
- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (2021)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels](https://mlsanity.com/paper/2101.05022/) (2021)
- [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020)
- [Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise](https://mlsanity.com/paper/2012.05458/) (2020)
- [Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition](https://mlsanity.com/paper/2207.10299/) (2022)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [Structured Semantic Transfer for Multi-Label Recognition with Partial Labels](https://mlsanity.com/paper/2112.10941/) (2021)
- [Large Loss Matters in Weakly Supervised Multi-Label Classification](https://mlsanity.com/paper/2206.03740/) (2022)
- [Multi-label Classification with Partial Annotations using Class-aware Selective Loss](https://mlsanity.com/paper/2110.10955/) (2021)
- [Acknowledging the Unknown for Multi-label Learning with Single Positive Labels](https://mlsanity.com/paper/2203.16219/) (2022)
- [Background Activation Suppression for Weakly Supervised Object Localization](https://mlsanity.com/paper/2112.00580/) (2021)
- [Multi-label Iterated Learning for Image Classification with Label Ambiguity](https://mlsanity.com/paper/2111.12172/) (2021)
- [Keep CALM and Improve Visual Feature Attribution](https://mlsanity.com/paper/2106.07861/) (2021)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)

## Built on by (most cited first, 11 of 11)

- [Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification](https://mlsanity.com/paper/2503.16873/) (2025)
- [Can Class-Priors Help Single-Positive Multi-Label Learning?](https://mlsanity.com/paper/2309.13886/) (2023)
- [Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels](https://mlsanity.com/paper/2401.16991/) (2024)
- [Exploring Partial Multi-Label Learning via Integrating Semantic Co-occurrence Knowledge](https://mlsanity.com/paper/2507.05992/) (2025)
- [PSScreen: Partially Supervised Multiple Retinal Disease Screening](https://mlsanity.com/paper/2508.10549/) (2025)
- [More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning](https://mlsanity.com/paper/2508.20381/) (2025)
- [Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classification](https://mlsanity.com/paper/2405.15860/) (2024)
- [A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trends](https://mlsanity.com/paper/2406.06119/) (2024)
- [The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning](https://mlsanity.com/paper/2508.21816/) (2025)
- [Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2510.08269/) (2025)
- [Hyperbolic Structured Classification for Robust Single Positive Multi-label Learning](https://mlsanity.com/paper/2510.15296/) (2025)

## Abstract (arXiv)

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.