AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentation

• URL: http://arxiv.org/abs/2409.08516v2
• Date: Mon, 30 Jun 2025 11:15:38 GMT
• Title: AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentation
• Authors: Zechao Sun, Shuying Piao, Haolin Jin, Chang Dong, Lin Yue, Weitong Chen, Luping Zhou,
• Abstract summary: We propose an enhanced approach called Adaptive Weight Fusion (AWF), which introduces an alternating training strategy for the fusion.<n>AWF achieves superior performance by better balancing the retention of old knowledge with the learning of new classes, significantly improving results on benchmark CISS tasks.
• Score: 17.754439732714307
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class Incremental Semantic Segmentation (CISS) aims to mitigate catastrophic forgetting by maintaining a balance between previously learned and newly introduced knowledge. Existing methods, primarily based on regularization techniques like knowledge distillation, help preserve old knowledge but often face challenges in effectively integrating new knowledge, resulting in limited overall improvement. Endpoints Weight Fusion (EWF) method, while simple, effectively addresses some of these limitations by dynamically fusing the model weights from previous steps with those from the current step, using a fusion parameter alpha determined by the relative number of previously known classes and newly introduced classes. However, the simplicity of the alpha calculation may limit its ability to fully capture the complexities of different task scenarios, potentially leading to suboptimal fusion outcomes. In this paper, we propose an enhanced approach called Adaptive Weight Fusion (AWF), which introduces an alternating training strategy for the fusion parameter, allowing for more flexible and adaptive weight integration. AWF achieves superior performance by better balancing the retention of old knowledge with the learning of new classes, significantly improving results on benchmark CISS tasks compared to the original EWF. And our experiment code will be released on Github.

Related papers

• EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning [53.88000987041739]
  Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time.<n>We propose the Elastic Knowledge Preservation and Compensation (EKPC) method, integrating Importance-aware importance Regularization (IPR) and Trainable Semantic Drift Compensation (TSDC) for CIL.
  arXiv  Detail & Related papers  (2025-06-14T05:19:58Z)
• Corrected with the Latest Version: Make Robust Asynchronous Federated Learning Possible [2.663489028501814]
  This paper proposes an asynchronous federated learning version correction algorithm based on knowledge distillation, named FedADT. FedADT applies knowledge distillation before aggregating gradients, using the latest global model to correct outdated information, thus effectively reducing the negative impact of outdated gradients on the training process. We conducted experimental comparisons with several classical algorithms, and the results demonstrate that FedADT achieves significant improvements over other asynchronous methods and outperforms all methods in terms of convergence speed.
  arXiv  Detail & Related papers  (2025-04-05T06:54:13Z)
• Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning [12.67816343247008]
  Class-incremental Learning enables the model to incrementally absorb knowledge from new classes. When the model optimize with new classes, the knowledge of previous classes is inevitably erased, leading to catastrophic forgetting.
  arXiv  Detail & Related papers  (2025-03-25T09:51:04Z)
• Feature Calibration enhanced Parameter Synthesis for CLIP-based Class-incremental Learning [10.253058594622017]
  Class-Incremental Learning (CIL) enables models to continuously learn new class knowledge while retaining previous classes. Traditional CIL methods rely primarily on visual features, which limits their effectiveness in complex, multimodal scenarios. We propose a Feature Enhanced Synthesis (FCPS) framework that mitigates catastrophic generalization while preserving the model's intrinsic generalization capability.
  arXiv  Detail & Related papers  (2025-03-24T13:44:12Z)
• ReconBoost: Boosting Can Achieve Modality Reconcilement [89.4377895465204]
  We study the modality-alternating learning paradigm to achieve reconcilement. We propose a new method called ReconBoost to update a fixed modality each time. We show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others.
  arXiv  Detail & Related papers  (2024-05-15T13:22:39Z)
• Continual Learning with Weight Interpolation [4.689826327213979]
  Continual learning requires models to adapt to new tasks while retaining knowledge from previous ones. This paper proposes a novel approach to continual learning utilizing the weight consolidation method.
  arXiv  Detail & Related papers  (2024-04-05T10:25:40Z)
• Enhanced Few-Shot Class-Incremental Learning via Ensemble Models [34.84881941101568]
  Few-shot class-incremental learning aims to continually fit new classes with limited training data. The main challenges are overfitting the rare new training samples and forgetting old classes. We propose a new ensemble model framework cooperating with data augmentation to boost generalization.
  arXiv  Detail & Related papers  (2024-01-14T06:07:07Z)
• FOSTER: Feature Boosting and Compression for Class-Incremental Learning [52.603520403933985]
  Deep neural networks suffer from catastrophic forgetting when learning new categories. We propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively.
  arXiv  Detail & Related papers  (2022-04-10T11:38:33Z)
• Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
  Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples. We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment. We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
  arXiv  Detail & Related papers  (2022-03-23T06:24:31Z)
• FedCostWAvg: A new averaging for better Federated Learning [1.1245087602142634]
  We propose a new aggregation strategy for federated learning that won the MICCAI Federated Tumor Challenge 2021. Our method addresses the problem of how to aggregate multiple models that were trained on different data sets.
  arXiv  Detail & Related papers  (2021-11-16T17:31:58Z)
• Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning [96.75889543560497]
  In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. We propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations.
  arXiv  Detail & Related papers  (2021-03-01T21:14:33Z)
• Meta-Learning with Adaptive Hyperparameters [55.182841228303225]
  We focus on a complementary factor in MAML framework, inner-loop optimization (or fast adaptation) We propose a new weight update rule that greatly enhances the fast adaptation process.
  arXiv  Detail & Related papers  (2020-10-31T08:05:34Z)
• Incremental Object Detection via Meta-Learning [77.55310507917012]
  We propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection.
  arXiv  Detail & Related papers  (2020-03-17T13:40:00Z)

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.