用封闭集关系知识提升开放世界类别发现的准确性与稳定性。
CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery
- 通过轻量适配器构建封闭集教师模型，保留预训练语义先验。
- 统一关系蒸馏同时学习全局原型关系与局部邻近结构，避免目标冲突。
- 兼容多种方法，六大数据集上均超越现有基线，效果显著。
广义类别发现（GCD）是一个引人关注的开放世界问题：给定部分标注数据，目标是在正确识别已知类别的同时，从无标签样本中发现结构一致的新类别。现有方法通常联合优化监督分类与无监督发现目标，但这种耦合训练易导致封闭集识别与开放集发现之间的目标冲突，引发预测偏差，并在标签有限、伪标签噪声多的情况下破坏预训练表示的语义几何。本文提出CloSeR，一种简单即插即用的框架，将封闭集关系知识注入GCD训练。CloSeR首先在已知类标注数据上微调轻量级块级适配器，构建领域适应的封闭集教师模型，同时冻结主干网络，以低成本保留预训练先验。随后通过统一关系蒸馏（URD）将教师知识迁移至下游GCD任务，分别蒸馏全局样本-原型关系以锚定已知类别语义，以及局部样本-样本关系以保持邻域结构，采用独立特征路径降低优化干扰。CloSeR无需特定头设计，可无缝集成于参数化与非参数化GCD方法。在六个基准数据集（CIFAR-10/100、ImageNet-100、CUB、Stanford-Cars、FGVC-Aircraft）上使用DINO和DINOv2主干进行的大量实验表明，其性能持续优于现有基线，达到当前最优水平。
原文摘要 · Abstract (English)
Generalized Category Discovery (GCD) is an intriguing open-world problem that has garnered increasing attention: given partially labelled data, the goal is to correctly recognize known classes while discovering coherent novel categories from unlabelled samples. Recent GCD methods typically adapt foundation models by jointly optimizing supervised classification and unsupervised discovery objectives on mixed labelled and unlabelled data. While effective, this coupled training can entangle closed-set recognition and open-set discovery, leading to objective conflict and biased predictions, and may disturb the semantic geometry of pretrained representations under limited labels and noisy pseudo-labels. We propose CloSeR, a simple plug-and-play framework that injects Closed-Set Relational knowledge into GCD training. CloSeR first builds a domain-adapted closed-set teacher by tuning lightweight block-wise adapters on labelled known-class data while keeping the foundation model backbone frozen, thereby preserving pretrained priors at low training cost. It then transfers the teacher's knowledge to downstream GCD via Unified Relational Distillation (URD), which distills complementary global sample-to-prototype relations to anchor known-class semantics and local sample-to-sample relations to preserve neighborhood structure, using separate feature pathways to reduce optimization interference. CloSeR is head-agnostic and readily integrates with both parametric and non-parametric GCD methods. Extensive experiments with DINO and DINOv2 backbones on six benchmarks (CIFAR-10/100, ImageNet-100, CUB, Stanford-Cars, and FGVC-Aircraft) show consistent gains over GCD baselines, achieving state-of-the-art performance. Project page: https://visual-ai.github.io/closer/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。