# Adaptive Discovering and Merging for Incremental Novel Class Discovery

arXiv: https://arxiv.org/abs/2403.03382 · HTML: https://mlsanity.com/paper/2403.03382/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion](https://mlsanity.com/paper/2111.11326/) (2021)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Adaptive Aggregation Networks for Class-Incremental Learning](https://mlsanity.com/paper/2010.05063/) (2020)
- [Automatically Discovering and Learning New Visual Categories with Ranking Statistics](https://mlsanity.com/paper/2002.05714/) (2020)
- [Learning to cluster in order to transfer across domains and tasks](https://mlsanity.com/paper/1711.10125/) (2017)
- [Learning Open Set Network with Discriminative Reciprocal Points](https://mlsanity.com/paper/2011.00178/) (2020)
- [Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation](https://mlsanity.com/paper/2204.00895/) (2022)
- [Multi-class Classification without Multi-class Labels](https://mlsanity.com/paper/1901.00544/) (2019)
- [Less-forgetting Learning in Deep Neural Networks](https://mlsanity.com/paper/1607.00122/) (2016)
- [OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World](https://mlsanity.com/paper/2004.05551/) (2020)
- [Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data](https://mlsanity.com/paper/2104.12673/) (2021)
- [ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks](https://mlsanity.com/paper/1811.10495/) (2018)
- [DiracNets: Training Very Deep Neural Networks Without Skip-Connections](https://mlsanity.com/paper/1706.00388/) (2017)

## Built on by (most cited first, 6 of 6)

- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2408.13373/) (2024)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network](https://mlsanity.com/paper/2506.17457/) (2025)
- [Continual Novel Class Discovery via Feature Enhancement and Adaptation](https://mlsanity.com/paper/2405.06389/) (2024)
- [MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning](https://mlsanity.com/paper/2408.13385/) (2024)

## Abstract (arXiv)

One important desideratum of lifelong learning aims to discover novel classes from unlabelled data in a continuous manner. The central challenge is twofold: discovering and learning novel classes while mitigating the issue of catastrophic forgetting of established knowledge. To this end, we introduce a new paradigm called Adaptive Discovering and Merging (ADM) to discover novel categories adaptively in the incremental stage and integrate novel knowledge into the model without affecting the original knowledge. To discover novel classes adaptively, we decouple representation learning and novel class discovery, and use Triple Comparison (TC) and Probability Regularization (PR) to constrain the probability discrepancy and diversity for adaptive category assignment. To merge the learned novel knowledge adaptively, we propose a hybrid structure with base and novel branches named Adaptive Model Merging (AMM), which reduces the interference of the novel branch on the old classes to preserve the previous knowledge, and merges the novel branch to the base model without performance loss and parameter growth. Extensive experiments on several datasets show that ADM significantly outperforms existing class-incremental Novel Class Discovery (class-iNCD) approaches. Moreover, our AMM also benefits the class-incremental Learning (class-IL) task by alleviating the catastrophic forgetting problem.