LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition
This work addresses the problem of open-set object recognition for computer vision applications, presenting an incremental improvement by combining existing models in a novel way.
The paper tackles open-set object recognition by reducing reliance on spurious-discriminative features through a training-free framework called Large Model Collaboration (LMC), which leverages distinct implicit knowledge from different pre-trained large models, achieving efficacy as demonstrated in extensive experiments.
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 https://github.com/Harryqu123/LMC