Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning
In our ever-evolving world, new data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without forgetting, addressing the challenge of long-tailed class-incremental learning (LTCIL). Existing methods often rely on retraining linear classifiers with former data, which is impractical in real-world settings. In this paper, we harness the potent representation capabilities of pre-trained models and introduce AdaPtive Adapter RouTing (APART) as an exemplar-free solution for LTCIL. To counteract forgetting, we train inserted adapters with frozen pre-trained weights for deeper adaptation and maintain a pool of adapters for selection during sequential model updates. Additionally, we present an auxiliary adapter pool designed for effective generalization, especially on minority classes. Adaptive instance routing across these pools captures crucial correlations, facilitating a comprehensive representation of all classes. Consequently, APART tackles the imbalance problem as well as catastrophic forgetting in a unified framework. Extensive benchmark experiments validate the effectiveness of APART. Code is available at: https://github.com/vita-qzh/APART
Code (1)
Tasks
class-incremental learningClass Incremental LearningExemplar-FreeIncremental LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Divide, Weight, and Route: Difficulty-Aware Optimization with Dynamic Expert Fusion for Long-tailed Recognition
Long-tailed visual recognition is challenging not only due to class imbalance but also because of varying classification difficulty across categories. Simply reweighting classes by frequency often overlooks those that ar…
POLAR: Online Learning for LoRA Adapter Caching and Routing in Edge LLM Serving
Edge deployment of large language models (LLMs) increasingly relies on libraries of lightweight LoRA adapters, yet GPU/DRAM can keep only a small resident subset at a time. Serving a request through a non-resident adapte…
Adaptive Minds: Empowering Agents with LoRA-as-Tools
We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke. We hypothesize that, when adapters are trained to provide strong domain-specif…
MASER: Modality-Adaptive Specialist Routing for Embodied 3D Spatial Intelligence
In 3D environments, Embodied Agents answer spatially relevant questions through reasoning from a mixture of modalities including natural language, RGB images, point clouds, depth maps and camera poses. Existing Vision-La…
Point CloudsLPT++: Efficient Training on Mixture of Long-tailed Experts
We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through …
Mixture-of-Expertsparameter-efficient fine-tuning