LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition
Haoxuan Qu, Xiaofei Hui, Yujun Cai, Jun Liu
Abstract
Open-set object recognition aims to identify if an object is from a class that has been encountered during training or not. To perform open-set object recognition accurately, a key challenge is how to reduce the reliance on spurious-discriminative features. In this paper, motivated by that different large models pre-trained through different paradigms can possess very rich while distinct implicit knowledge, we propose a novel framework named Large Model Collaboration (LMC) to tackle the above challenge via collaborating different off-the-shelf large models in a training-free manner. Moreover, we also incorporate the proposed framework with several novel designs to effectively extract implicit knowledge from large models. Extensive experiments demonstrate the efficacy of our proposed framework. Code is available \href{https://github.com/Harryqu123/LMC}{here}.
BibTeX
@inproceedings{
qu2023lmc,
title={{LMC}: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition},
author={Haoxuan Qu and Xiaofei Hui and Yujun Cai and Jun Liu},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=dHF3Im8Aic}
}