# Specifying What You Know or Not for Multi-Label Class-Incremental Learning

arXiv: https://arxiv.org/abs/2503.17017 · HTML: https://mlsanity.com/paper/2503.17017/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 17 of 17)

- [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)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion](https://mlsanity.com/paper/2111.11326/) (2021)
- [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)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification](https://mlsanity.com/paper/1912.07872/) (2019)
- [Imbalanced Continual Learning with Partitioning Reservoir Sampling](https://mlsanity.com/paper/2009.03632/) (2020)
- [Multi-View Correlation Distillation for Incremental Object Detection](https://mlsanity.com/paper/2107.01787/) (2021)
- [Order-Free RNN with Visual Attention for Multi-Label Classification](https://mlsanity.com/paper/1707.05495/) (2017)
- [Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning](https://mlsanity.com/paper/2209.11469/) (2022)

## Built on by (most cited first, 4 of 4)

- [Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detection](https://mlsanity.com/paper/2606.15253/) (2026)
- [Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection](https://mlsanity.com/paper/2607.17340/) (2026)
- [P2L-CA: An Effective Parameter Tuning Framework for Rehearsal-Free Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2601.12714/) (2026)
- [Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2608.30316/) (2026)

## Abstract (arXiv)

Existing class incremental learning is mainly designed for single-label classification task, which is ill-equipped for multi-label scenarios due to the inherent contradiction of learning objectives for samples with incomplete labels. We argue that the main challenge to overcome this contradiction in multi-label class-incremental learning (MLCIL) lies in the model's inability to clearly distinguish between known and unknown knowledge. This ambiguity hinders the model's ability to retain historical knowledge, master current classes, and prepare for future learning simultaneously. In this paper, we target at specifying what is known or not to accommodate Historical, Current, and Prospective knowledge for MLCIL and propose a novel framework termed as HCP. Specifically, (i) we clarify the known classes by dynamic feature purification and recall enhancement with distribution prior, enhancing the precision and retention of known information. (ii) We design prospective knowledge mining to probe the unknown, preparing the model for future learning. Extensive experiments validate that our method effectively alleviates catastrophic forgetting in MLCIL, surpassing the previous state-of-the-art by 3.3% on average accuracy for MS-COCO B0-C10 setting without replay buffers.