CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors
This work addresses COVID-19 diagnosis for medical imaging applications, but it is incremental as it builds on a prior winning solution with specific improvements.
The paper tackled COVID-19 detection from videos by enhancing a baseline 3D contrastive mixup classification network with natural video priors and advanced training strategies, achieving first place in a competition with an average Macro F1 Score of 89.11%.
This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop at the European Conference on Computer Vision (ECCV 2022). In our approach, we employ the winning solution last year which uses a strong 3D Contrastive Mixup Classifcation network (CMC v1) as the baseline method, composed of contrastive representation learning and mixup classification. In this paper, we propose CMC v2 by introducing natural video priors to COVID-19 diagnosis. Specifcally, we adapt a pre-trained (on video dataset) video transformer backbone to COVID-19 detection. Moreover, advanced training strategies, including hybrid mixup and cutmix, slicelevel augmentation, and small resolution training are also utilized to boost the robustness and the generalization ability of the model. Among 14 participating teams, CMC v2 ranked 1st in the 2nd COVID-19 Competition with an average Macro F1 Score of 89.11%.