paper-with-me

Papers

Upcycling Models under Domain and Category Shift

2023-03-13 · CVPR 2023 1 · Sanqing Qu, Tianpei Zou, Florian Roehrbein, Cewu Lu, Guang Chen, DaCheng Tao, Changjun Jiang

Deep neural networks (DNNs) often perform poorly in the presence of domain shift and category shift. How to upcycle DNNs and adapt them to the target task remains an important open problem. Unsupervised Domain Adaptation (UDA), especially recently proposed Source-free Domain Adaptation (SFDA), has become a promising technology to address this issue. Nevertheless, existing SFDA methods require that the source domain and target domain share the same label space, consequently being only applicable to the vanilla closed-set setting. In this paper, we take one step further and explore the Source-free Universal Domain Adaptation (SF-UniDA). The goal is to identify "known" data samples under both domain and category shift, and reject those "unknown" data samples (not present in source classes), with only the knowledge from standard pre-trained source model. To this end, we introduce an innovative global and local clustering learning technique (GLC). Specifically, we design a novel, adaptive one-vs-all global clustering algorithm to achieve the distinction across different target classes and introduce a local k-NN clustering strategy to alleviate negative transfer. We examine the superiority of our GLC on multiple benchmarks with different category shift scenarios, including partial-set, open-set, and open-partial-set DA. Remarkably, in the most challenging open-partial-set DA scenario, GLC outperforms UMAD by 14.8\% on the VisDA benchmark. The code is available at https://github.com/ispc-lab/GLC.

📄 PDF Abstract BibTeX arXiv:2303.07110

Code (3)

ispc-lab/glc 공식 구현 pytorch
ispc-lab/bmd pytorch
ispc-lab/glc-plus pytorch

Tasks

ClusteringDomain AdaptationSource-Free Domain AdaptationUniversal Domain AdaptationUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

k-NN $k$-Nearest Neighbors is a clustering-based algorithm for classification and regression. It is a a type of instance-based learning as it does not attempt to construct a…

Similar Papers 제목 키워드 기반

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts

2026-04-21 · Chaitanya Dwivedi, Binxuan Huang, Himanshu Gupta, Pratik Jayarao 외 arxiv

Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation through sparse expert routing. Scaling laws …

Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling

2025-08-31 · Junfeng Ran, Guangxiang Zhao, Yuhan Wu, Dawei Zhu 외 arxiv

The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. However, efficiently training these models re…

Upcycling Large Language Models into Mixture of Experts

2024-10-10 · Ethan He, Abhinav Khattar, Ryan Prenger, Vijay Korthikanti 외

Upcycling pre-trained dense language models into sparse mixture-of-experts (MoE) models is an efficient approach to increase the model capacity of already trained models. However, optimal techniques for upcycling at scal…

Mixture-of-ExpertsMMLU

UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes

2022-11-22 · ICCV 2023 1 · Sunwook Hwang, Youngseok Kim, Seongwon Kim, Saewoong Bahk 외

Semi-supervised Learning (SSL) has received increasing attention in autonomous driving to reduce the enormous burden of 3D annotation. In this paper, we propose UpCycling, a novel SSL framework for 3D object detection wi…

3D Object DetectionAutonomous DrivingAutonomous VehiclesDomain Adaptation+3

SPRI: SVD-Partitioned Residual Initialization for Data-Constrained MoE Upcycling

2026-06-15 · Weiqiao Shan, Ruixiang Mao, Yuang Li, Yuhao Zhang 외 arxiv

Mixture-of-Experts (MoE) models enable efficient scaling, but training them from scratch remains prohibitively expensive. MoE upcycling mitigates this cost by converting pretrained dense models into sparse MoE models. Ho…

Speech-to-Text Translation