# Dual-Imbalance Continual Learning for Real-World Food Recognition

arXiv: https://arxiv.org/abs/2603.29133 · HTML: https://mlsanity.com/paper/2603.29133/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 62 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model](https://mlsanity.com/paper/2303.05118/) (2023)
- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [Model merging with SVD to tie the Knots](https://mlsanity.com/paper/2410.19735/) (2024)
- [Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2403.12030/) (2024)
- [Memory-Efficient Incremental Learning Through Feature Adaptation](https://mlsanity.com/paper/2004.00713/) (2020)
- [Influence-Balanced Loss for Imbalanced Visual Classification](https://mlsanity.com/paper/2110.02444/) (2021)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning](https://mlsanity.com/paper/2403.18886/) (2024)
- [VisPlay: Self-Evolving Vision-Language Models from Images](https://mlsanity.com/paper/2511.15661/) (2025)
- [Dense Network Expansion for Class Incremental Learning](https://mlsanity.com/paper/2303.12696/) (2023)
- [Online Continual Learning For Visual Food Classification](https://mlsanity.com/paper/2108.06781/) (2021)
- [Visual Aware Hierarchy Based Food Recognition](https://mlsanity.com/paper/2012.03368/) (2020)
- [Long-Tailed Class Incremental Learning](https://mlsanity.com/paper/2210.00266/) (2022)
- [MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2412.09441/) (2024)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning](https://mlsanity.com/paper/2505.24816/) (2025)
- [Dynamic Residual Classifier for Class Incremental Learning](https://mlsanity.com/paper/2308.13305/) (2023)

## Abstract (arXiv)

Visual food recognition in real-world dietary logging scenarios naturally exhibits severe data imbalance, where a small number of food categories appear frequently while many others occur rarely, resulting in long-tailed class distributions. In practice, food recognition systems often operate in a continual learning setting, where new categories are introduced sequentially over time. However, existing studies typically assume that each incremental step introduces a similar number of new food classes, which rarely happens in real world where the number of newly observed categories can vary significantly across steps, leading to highly uneven learning dynamics. As a result, continual food recognition exhibits a dual imbalance: imbalanced samples within each food class and imbalanced numbers of new food classes to learn at each incremental learning step. In this work, we introduce DIME, a Dual-Imbalance-aware Adapter Merging framework for continual food recognition. DIME learns lightweight adapters for each task using parameter-efficient fine-tuning and progressively integrates them through a class-count guided spectral merging strategy. A rank-wise threshold modulation mechanism further stabilizes the merging process by preserving dominant knowledge while allowing adaptive updates. The resulting model maintains a single merged adapter for inference, enabling efficient deployment without accumulating task-specific modules. Experiments on realistic long-tailed food benchmarks under our step-imbalanced setup show that the proposed method consistently improves by more than 3% over the strongest existing continual learning baselines. Code is available at https://github.com/xiaoyanzhang1/DIME.