基于解耦目标性学习与类别识别的持续分割

Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation

Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental semantic segmentation, such a phenomenon often becomes much worse due to the background shift, i.e., some concepts learned at previous stages are assigned to the background class at the current training stage, therefore, significantly reducing the performance of these old concepts. To address this issue, we propose a simple yet effective method in this paper,…

Disentanglement of Color and Shape Representations for Continual Learning

We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification accuracy and forgetting in a task-incremental setting with Oxford-102 Flowers dataset. We combine our method with Elastic Weight Consolidation, Learning without Forgetting, Synaptic Intelligence and Memory Aware Synapses, and show that feature disentanglement positively impacts continual learning performance.

用于解耦持续学习的 Infinite dSprites：将记忆编辑与泛化分离

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization

本文提出 Infinite dSprites 基准工具，揭示持续学习方法在长任务序列下性能下降问题，并通过学习类不可知变换来规避灾难性遗忘，实现显式控制记忆与遗忘的开放集分类及单样本泛化。

用于少样本目标检测的注意力解耦均匀正交特征空间优化

Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection

针对少样本目标检测中目标性识别与分类纠缠的问题，提出均匀正交特征空间优化框架，通过幅值与角度解耦、混合背景优化策略及空间注意力模块，显著提升了检测性能。

重新思考基于查询的Transformer用于持续图像分割

Rethinking Query-based Transformer for Continual Image Segmentation

针对持续图像分割中解耦框架的可塑性丧失和数据顺序依赖问题，提出SimCIS基线，通过直接选择图像特征进行查询分配以保持客观性并促进可塑性，并引入跨阶段一致性和视觉查询重放机制对抗灾难性遗忘，在多种任务和设置上优于现有方法。

Learning Invariant Representation for Continual Learning

Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting previously learned tasks when the agent faces a new one. Current rehearsal-based methods show their success in mitigating the catastrophic forgetting problem by replaying samples from previous tasks during learning a new one. However, these methods are infeasible when the data of previous tasks is not accessible. In this work, we propose a new pseudo-rehearsal-based …