Search papers, labs, and topics across Lattice.
CloSeR introduces a novel approach to Generalized Category Discovery (GCD) by leveraging Closed-Set Relational knowledge through a framework that employs Unified Relational Distillation (URD). This method effectively separates the tasks of closed-set recognition and open-set discovery, mitigating conflicts that arise from traditional coupled training methods. Experimental results across six benchmarks demonstrate that CloSeR consistently outperforms existing GCD baselines, achieving state-of-the-art results while preserving the semantic integrity of pretrained models.
CloSeR achieves state-of-the-art GCD performance by elegantly decoupling closed-set recognition from open-set discovery, minimizing objective conflicts and enhancing semantic coherence.
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/
