Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning

• URL: http://arxiv.org/abs/2605.29592v1
• Date: Thu, 28 May 2026 08:34:14 GMT
• Title: Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning
• Abstract summary: Class-Incremental Learning (CIL) with pre-trained models (PTMs) aims to sequentially adapt PTMs to new categories without forgetting old knowledge.<n>Existing adapter-based methods mainly train models via distinct task-specific adapters.<n>We propose a Non-Forgetting Allocation with Bi-Level Competition (NoFA-BC)
• Score: 86.93181780690372
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-Incremental Learning (CIL) with pre-trained models (PTMs) aims to sequentially adapt PTMs to new categories without forgetting old knowledge. Built upon PTMs, existing adapter-based methods mainly train models via distinct task-specific adapters, and present a uniform knowledge allocation for each adapter during inference. However, this allocation mechanism ignores the nature of task discrepancy and leads to suboptimal utilization of adapters. Also, under CIL constraint, an allocator is prone to forgetting when tasks evolve. To address these issues, we propose a Non-Forgetting Allocation with Bi-Level Competition (NoFA-BC). NoFA-BC constructs a non-forgetting allocator (NFA) by transforming the allocator training into a recursive least-squares problem and achieves an allocator equivalent to that trained with all data. Based on the NFA, a Bi-Level Competition (BLC) including an intra-task level Winner-Takes-All (WTA) mechanism and inter-task Last-Ones-Fall (LOF) elimination is proposed to provide better allocation of adapter knowledge. WTA extracts the most significant logit within a task to represent the adapter's contribution and LOF suppresses the irrelevant adapters. With BLC, participation ratio of each adapter can be tailored for each input. Moreover, a Stability Enhancement (SE) process is incorporated to further improve the performance of old tasks.

Related papers

• Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning [33.57130798344366]
  We propose integrating Task-Specific and Universal Adapters (TUNA) in this paper.<n> Specifically, we train task-specific adapters to capture the most crucial features relevant to their respective tasks.<n>We leverage an adapter fusion strategy to construct a universal adapter, which encodes the most discriminative features shared across tasks.
  arXiv  Detail & Related papers  (2025-08-11T16:41:04Z)
• DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition [59.203152078315235]
  Open-Vocabulary Multi-Label Recognition (OV-MLR) aims to identify multiple seen and unseen object categories within an image.<n> Vision-Language Pre-training models offer a strong open-vocabulary foundation, but struggle with fine-grained localization under weak supervision.<n>We propose the Dual Adaptive Refinement Transfer (DART) framework to overcome these limitations.
  arXiv  Detail & Related papers  (2025-08-07T17:22:33Z)
• CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning [80.18781219542016]
  Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.<n>Recent parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance.<n>We propose Cross-subspace Knowledge Alignment and Aggregation (CKAA) to enhance robustness against misleading task-ids.
  arXiv  Detail & Related papers  (2025-07-13T03:11:35Z)
• CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning [8.81873424028249]
  Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes.<n>We propose a novel dual-adapter architecture combining textbftask-shared adapters to learn cross-task knowledge and textbftask-specific adapters to capture unique features of each new task.<n>We demonstrate CL-LoRA consistently achieves promising performance under multiple benchmarks with reduced training and inference computation.
  arXiv  Detail & Related papers  (2025-05-30T17:19:52Z)
• CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation [75.35841972192684]
  Effective Class Incremental (CIS) requires simultaneously mitigating catastrophic forgetting and ensuring sufficient plasticity to integrate new classes.<n>We introduce a novel approach, Conflict Mitigation via Branched Optimization(CoMBO)<n>Within this approach, we present the Query Conflict Reduction module, designed to explicitly refine queries for new classes.
  arXiv  Detail & Related papers  (2025-04-05T12:34:51Z)
• AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discovery [15.640670797555579]
  Generalized Category Discovery aims to classify old categories and discover new categories in the unlabeled data.<n>Existing studies on GCD typically devote to transferring the general knowledge from the self-supervised pretrained model to the target GCD task.<n>We propose a novel adapter-tuning-based method named AdaptGCD, which is the first work to introduce the adapter tuning into the GCD task.
  arXiv  Detail & Related papers  (2024-10-29T03:41:47Z)
• Dynamic Integration of Task-Specific Adapters for Class Incremental Learning [32.124078616314144]
  Non-exemplar class Incremental Learning (NECIL) enables models to continuously acquire new classes without retraining from scratch and storing old task exemplars.<n>We propose a novel framework called Dynamic Integration of task-specific Adapters (DIA), which comprises two key components: Task-Specific Adapter Integration (TSAI) and Patch-Level Model Alignment.
  arXiv  Detail & Related papers  (2024-09-23T13:01:33Z)
• Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning [55.384428765798496]
  New data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without forgetting. We introduce AdaPtive Adapter RouTing (APART) as an exemplar-free solution for LTCIL.
  arXiv  Detail & Related papers  (2024-09-11T17:52:00Z)
• I2I: Initializing Adapters with Improvised Knowledge [15.452979531094567]
  Improvise for. I2LiI, a continual learning algorithm, initializes Adapters for incoming tasks by distilling. previously-learned tasks. I2I consistently achieves better task accuracy than independently-trained Adapters.
  arXiv  Detail & Related papers  (2023-04-04T23:51:48Z)
• Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters [59.82088750033897]
  We set up a Generalized FSCL (GFSCL) protocol involving both class- and domain-incremental situations. We find that common continual learning methods have poor generalization ability on unseen domains. In this way, we propose a rehearsal-free framework based on Vision Transformer (ViT) named Contrastive Mixture of Adapters (CMoA)
  arXiv  Detail & Related papers  (2023-02-12T15:18:14Z)
• Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification [57.36281142038042]
  We present a new adaptive block called Contextual Squeeze-and-Excitation (CaSE) that adjusts a pretrained neural network on a new task to significantly improve performance. We also present a new training protocol based on Coordinate-Descent called UpperCaSE that exploits meta-trained CaSE blocks and fine-tuning routines for efficient adaptation.
  arXiv  Detail & Related papers  (2022-06-20T15:25:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.