发表机构
The University of Hong Kong（香港大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出即插即用框架CloSeR，通过闭集关系知识注入与统一关系蒸馏，提升广义类别发现性能，在六个基准上用DINO和DINOv2主干达到SOTA
AI 中文摘要
广义类别发现（GCD）是一个引人关注的开放世界问题，受到越来越多的关注：给定部分标注数据，目标是正确识别已知类别，同时从未标注样本中发现连贯的新类别。近期的GCD方法通常通过在混合标注和未标注数据上联合优化监督分类和无监督发现目标来适配基础模型。虽然有效，但这种耦合训练会混淆闭集识别和开放集发现，导致目标冲突和预测偏差，并且在有限标注和嘈杂伪标签下可能干扰预训练表示的语义几何。我们提出CloSeR，一个简单的即插即用框架，将闭集关系知识注入GCD训练。CloSeR首先通过在标注的已知类别数据上调轻量的块级适配器，同时保持基础模型主干冻结，构建域适配的闭集教师，从而以低训练成本保留预训练先验。然后它通过统一关系蒸馏（URD）将教师的知识迁移到下游GCD，URD蒸馏互补的全局样本到原型关系以锚定已知类别语义，以及局部样本到样本关系以保留邻域结构，使用单独的特征路径减少优化干扰。CloSeR与头部无关，可轻松集成到参数化和非参数化GCD方法中。在六个基准（CIFAR-10/100、ImageNet-100、CUB、Stanford-Cars和FGVC-Aircraft）上使用DINO和DINOv2主干进行的广泛实验表明，其相比GCD基线取得了一致的提升，达到了最先进的性能。项目页面：this https URL
英文摘要
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/
CommentsAccepted as a conference paper at ECCV 2026
