arXiv Computer Vision By Yuanpei Liu, Zhenqi He, Jialu Tang, Kai Han

CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery

Read the original on arXiv Computer Vision →

CloSeR is a plug‑and‑play framework that enhances Generalized Category Discovery (GCD) by injecting closed‑set relational knowledge from a lightweight teacher model. The teacher is built by fine‑tuning adapters on labeled data while keeping the backbone frozen, preserving pretrained priors. Unified Relational Distillation then transfers both global sample‑to‑prototype and local sample‑to‑sample relations to the GCD task, reducing optimization interference and improving performance across six benchmarks with DINO and DINOv2 backbones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision
Aug 24

Semantically Compatible Knowledge Distillation for Cross-Domain Object Detection with Vision Foundation Models

The paper introduces Semantic Localization-Enhanced Teacher (SLE‑T), a knowledge‑distillation framework that aligns spatial‑scale and semantic features between a Vision Foundation Model (VFM) teacher and a student detector for cross‑domain object detection. SLE‑T employs a lightweight SLE Adapter that injects pretrained local‑texture priors into DINOv2 and reformulates its features into dense, spatially and semantically compatible representations, enabling effective pseudo‑label learning or feature alignment. Experiments on three domain‑adaptive object detection benchmarks show that SLE‑T with DINOv2‑B achieves state‑of‑the‑art performance while using only a quarter of the training time and less GPU memory compared to the larger DINOv2‑G teacher.

By Qifeng Zhang, Ting Xiang, Zeyuan Bai, Changjian Chen