# AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition

arXiv: https://arxiv.org/abs/2203.05534 · HTML: https://mlsanity.com/paper/2203.05534/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 10 Mar 2022.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Imbalanced Continual Learning with Partitioning Reservoir Sampling](https://mlsanity.com/paper/2009.03632/) (2020)
- [Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition](https://mlsanity.com/paper/2009.09450/) (2020)
- [Deep Cross-Modal Hashing](https://mlsanity.com/paper/1602.02255/) (2016)
- [Multi-Label Learning with Global and Local Label Correlation](https://mlsanity.com/paper/1704.01415/) (2017)
- [Multi-Domain Multi-Task Rehearsal for Lifelong Learning](https://mlsanity.com/paper/2012.07236/) (2020)
- [Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging](https://mlsanity.com/paper/1604.05225/) (2016)
- [Coarse to Fine: Multi-label Image Classification with Global/Local Attention](https://mlsanity.com/paper/2012.13662/) (2020)
- [Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing](https://mlsanity.com/paper/2110.11159/) (2021)

## Built on by (most cited first, 16 of 16)

- [Exploring Example Influence in Continual Learning](https://mlsanity.com/paper/2209.12241/) (2022)
- [Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning](https://mlsanity.com/paper/2209.11469/) (2022)
- [Multi-Label Continual Learning using Augmented Graph Convolutional Network](https://mlsanity.com/paper/2211.14763/) (2022)
- [Knowledge Restore and Transfer for Multi-label Class-Incremental Learning](https://mlsanity.com/paper/2302.13334/) (2023)
- [Confidence Self-Calibration for Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2403.12559/) (2024)
- [Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation](https://mlsanity.com/paper/2503.22136/) (2025)
- [Centroid Distance Distillation for Effective Rehearsal in Continual Learning](https://mlsanity.com/paper/2303.02954/) (2023)
- [Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2310.20268/) (2023)
- [Elastic Multi-Gradient Descent for Parallel Continual Learning](https://mlsanity.com/paper/2401.01054/) (2024)
- [Overcoming Domain Drift in Online Continual Learning](https://mlsanity.com/paper/2405.09133/) (2024)
- [Rebalancing Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2408.12161/) (2024)
- [Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning](https://mlsanity.com/paper/2503.00515/) (2025)
- [Two-level Graph Network for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2303.13862/) (2023)
- [Multi-label Class Incremental Emotion Decoding with Augmented Emotional Semantics Learning](https://mlsanity.com/paper/2405.20600/) (2024)
- [Towards stable training of parallel continual learning](https://mlsanity.com/paper/2407.08214/) (2024)
- [P2L-CA: An Effective Parameter Tuning Framework for Rehearsal-Free Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2601.12714/) (2026)

## Abstract (arXiv)

The Lifelong Multi-Label (LML) image recognition builds an online class-incremental classifier in a sequential multi-label image recognition data stream. The key challenges of LML image recognition are the construction of label relationships on Partial Labels of training data and the Catastrophic Forgetting on old classes, resulting in poor generalization. To solve the problems, the study proposes an Augmented Graph Convolutional Network (AGCN) model that can construct the label relationships across the sequential recognition tasks and sustain the catastrophic forgetting. First, we build an Augmented Correlation Matrix (ACM) across all seen classes, where the intra-task relationships derive from the hard label statistics while the inter-task relationships leverage both hard and soft labels from data and a constructed expert network. Then, based on the ACM, the proposed AGCN captures label dependencies with dynamic augmented structure and yields effective class representations. Last, to suppress the forgetting of label dependencies across old tasks, we propose a relationship-preserving loss as a constraint to the construction of label relationships. The proposed method is evaluated using two multi-label image benchmarks and the experimental results show that the proposed method is effective for LML image recognition and can build convincing correlation across tasks even if the labels of previous tasks are missing. Our code is available at https://github.com/Kaile-Du/AGCN.