# Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training

arXiv: https://arxiv.org/abs/2404.06287 · HTML: https://mlsanity.com/paper/2404.06287/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 47 references that are in the map.
- First posted on arXiv 9 Apr 2024.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Query2Label: A Simple Transformer Way to Multi-Label Classification](https://mlsanity.com/paper/2107.10834/) (2021)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition](https://mlsanity.com/paper/1908.07325/) (2019)
- [Visual Commonsense R-CNN](https://mlsanity.com/paper/2002.12204/) (2020)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Multi-label Image Recognition by Recurrently Discovering Attentional Regions](https://mlsanity.com/paper/1711.02816/) (2017)
- [Extreme clicking for efficient object annotation](https://mlsanity.com/paper/1708.02750/) (2017)
- [Causal Attention for Unbiased Visual Recognition](https://mlsanity.com/paper/2108.08782/) (2021)
- [Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification](https://mlsanity.com/paper/1912.07872/) (2019)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [Multi-Label Classification with Label Graph Superimposing](https://mlsanity.com/paper/1911.09243/) (2019)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition](https://mlsanity.com/paper/2007.01755/) (2020)
- [Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition](https://mlsanity.com/paper/1712.07465/) (2017)
- [Structured Semantic Transfer for Multi-Label Recognition with Partial Labels](https://mlsanity.com/paper/2112.10941/) (2021)
- [Exploit Bounding Box Annotations for Multi-label Object Recognition](https://mlsanity.com/paper/1504.05843/) (2015)

## Built on by (most cited first, 8 of 8)

- [CF-VLM:CounterFactual Vision-Language Fine-tuning](https://mlsanity.com/paper/2506.17267/) (2025)
- [MAT-Agent: Adaptive Multi-Agent Training Optimization](https://mlsanity.com/paper/2510.17845/) (2025)
- [Text-Region Matching for Multi-Label Image Recognition with Missing Labels](https://mlsanity.com/paper/2407.18520/) (2024)
- [Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning](https://mlsanity.com/paper/2504.09990/) (2025)
- [Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning](https://mlsanity.com/paper/2407.18624/) (2024)
- [Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition](https://mlsanity.com/paper/2510.26466/) (2025)
- [FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning](https://mlsanity.com/paper/2604.28024/) (2026)
- [Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook](https://mlsanity.com/paper/2607.00839/) (2026)

## Abstract (arXiv)

The key to multi-label image classification (MLC) is to improve model performance by leveraging label correlations. Unfortunately, it has been shown that overemphasizing co-occurrence relationships can cause the overfitting issue of the model, ultimately leading to performance degradation. In this paper, we provide a causal inference framework to show that the correlative features caused by the target object and its co-occurring objects can be regarded as a mediator, which has both positive and negative impacts on model predictions. On the positive side, the mediator enhances the recognition performance of the model by capturing co-occurrence relationships; on the negative side, it has the harmful causal effect that causes the model to make an incorrect prediction for the target object, even when only co-occurring objects are present in an image. To address this problem, we propose a counterfactual reasoning method to measure the total direct effect, achieved by enhancing the direct effect caused only by the target object. Due to the unknown location of the target object, we propose patching-based training and inference to accomplish this goal, which divides an image into multiple patches and identifies the pivot patch that contains the target object. Experimental results on multiple benchmark datasets with diverse configurations validate that the proposed method can achieve state-of-the-art performance.