DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning

• URL: http://arxiv.org/abs/2607.01630v1
• Date: Thu, 02 Jul 2026 02:57:58 GMT
• Title: DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning
• Abstract summary: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or computationworks.<n>We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, and under-optimized shared representations in the backbone.<n>We propose the Decoupled Representation Dynamic Network (DRDN), which addresses these challenges via two mechanisms.
• Score: 6.097306160389619
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classification supervision alone does not sufficiently preserve task-agnostic shared backbone representations over long incremental sequences. We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, which biases decision boundaries toward recent tasks; and under-optimized shared representations in the backbone that cap long-term discriminability as tasks accumulate. We propose the Decoupled Representation Dynamic Network (DRDN), which addresses these challenges via two orthogonal mechanisms. For shared backbone representations, DRDN continuously applies masked image modeling (MIM) at every incremental step, with reconstruction gradients routed exclusively through the backbone, encouraging it to retain general visual structure beyond class-discriminative cues. For task-specific discrimination, DRDN employs hierarchical task token expansion across all transformer layers, with a modified per-task attention rule that reduces inter-task interference. We support this design with accuracy degradation analysis and cross-task confusion rate measurements. In the from-scratch ViT CIL setting (no external pretraining), DRDN consistently improves over strong token-expansion baselines with comparable backbone scale. On CIFAR100-B0 (10 steps), DRDN achieves 77.19% average accuracy, outperforming DKT by 1.36 points and DyTox by 3.53 points, with an advantage that grows at longer incremental sequences. Multi-seed validation confirms stability (+/-0.31%). The MIM decoder is active only during training, adding no inference-time parameters or computation.

Related papers

• Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling [61.28599393707943]
  Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps.<n>We propose a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment.<n> Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03% of dense understanding performance with a 1.93times$ end-to-end inference speedup.
  arXiv  Detail & Related papers  (2026-08-29T14:27:55Z)
• IntHQ: Task-Interactive Hierarchical Query on Dual-Stream Representations for Generative Recommendation [20.546679348797905]
  We show that existing multi-taskers are inherently prone to a threefold collapse.<n>We propose InHQ, a multi-task generative recommender with three components each alleviating one collapse.<n>In offline evaluations, InHQ consistently outperforms competitive backbones under four representative task-head configurations.
  arXiv  Detail & Related papers  (2026-08-10T14:13:47Z)
• Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning [14.508049757681862]
  LLM-powered coding agents spend the majority of their token budget reading repository files.<n>We show that this formulation creates a modeling bottleneck.<n>We propose LaMR, a structured pruning framework that decomposes code relevance into two interpretable quality dimensions.
  arXiv  Detail & Related papers  (2026-05-14T18:30:10Z)
• StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs [9.912407135967836]
  We introduce Streaming CVIT (StrCVIT), where models learn from a stream of data chunks containing a dynamic mixture of tasks.<n>In StrCVIT, a model must simultaneously acquire new abilities, reinforce recurring abilities, and forgetting.<n>We propose StrLoRA, a regularized two-stage expert routing framework.
  arXiv  Detail & Related papers  (2026-05-08T06:16:37Z)
• Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation [22.025559532445012]
  We propose STAMP (Semantic Trimming and Auxiliary Multi-step Prediction), a framework utilizing a dual-end optimization strategy.<n>Experiments on public Amazon and large-scale industrial datasets show STAMP achieves 1.23--1.38$times$ speedup and 17.2%--54.7% VRAM reduction.
  arXiv  Detail & Related papers  (2026-04-07T02:00:23Z)
• CORAL: Scalable Multi-Task Robot Learning via LoRA Experts [49.759823970016974]
  Vision-Language-Action (VLA) models in real-world robotics expose a core multi-task learning challenge.<n>Maintaining a separate full checkpoint per task is often storage- and deployment-prohibitive.<n>We present CORAL, a backbone- and-agnostic framework designed primarily to mitigate multi-task interference.
  arXiv  Detail & Related papers  (2026-03-10T07:28:41Z)
• GRID: Scalable Task-Agnostic Prompt-Based Continual Learning for Language Models [22.312673721170388]
  Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences.<n>Most existing methods rely on task-aware inference and maintain a growing set of task-specific prompts.<n>We present GRID, a unified framework designed to address these challenges.
  arXiv  Detail & Related papers  (2025-07-19T19:15:03Z)
• 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)
• Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism [120.1998866178014]
  We present a flexible framework for continual object detection via pRotOtypical taSk corrElaTion guided gaTingAnism (ROSETTA) Concretely, a unified framework is shared by all tasks while task-aware gates are introduced to automatically select sub-models for specific tasks. Experiments on COCO-VOC, KITTI-Kitchen, class-incremental detection on VOC and sequential learning of four tasks show that ROSETTA yields state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-05-06T07:31:28Z)
• Multi-task Over-the-Air Federated Learning: A Non-Orthogonal Transmission Approach [52.85647632037537]
  We propose a multi-task over-theair federated learning (MOAFL) framework, where multiple learning tasks share edge devices for data collection and learning models under the coordination of a edge server (ES) Both the convergence analysis and numerical results demonstrate that the MOAFL framework can significantly reduce the uplink bandwidth consumption of multiple tasks without causing substantial learning performance degradation.
  arXiv  Detail & Related papers  (2021-06-27T13:09:32Z)
• Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [87.1188556802942]
  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. We propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.
  arXiv  Detail & Related papers  (2021-05-17T13:42:09Z)

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.