This paper introduces a novel approach to leverage features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art self-supervised learning methods, DINO and data2vec, were evaluated and compared for their representation learning of vehicle images. The former contrasts local and global views while the latter uses masked prediction on multi-layered representations. In the latter case, supervised learning is employed to finetune a pretrained YOLOR object detector for detecting vehicle wheels, from which definitive wheel positional features are retrieved. The representations learned from these self-supervised learning methods were combined with the wheel positional features for the vehicle classification task. Particularly, a random wheel masking strategy was utilized to finetune the previously learned representations in harmony with the wheel positional features during the training of the classifier. Our experiments show that the data2vec-distilled representations, which are consistent with our wheel masking strategy, outperformed the DINO counterpart, resulting in a celebrated Top-1 classification accuracy of 97.2% for classifying the 13 vehicle classes defined by the Federal Highway Administration.

翻译：本文提出了一种新颖方法，通过融合监督与自监督两种范式下学习的特征来提升图像分类任务性能，特别针对车辆分类场景。我们评估并比较了两种前沿自监督学习方法——DINO与data2vec——对车辆图像的表征学习能力：前者通过对比局部与全局视图实现特征学习，后者则采用多层表征上的掩码预测策略。在后一方案中，我们利用监督学习微调预训练的YOLOR目标检测器以检测车辆轮毂，从而提取确定的轮毂位置特征。将自监督学习方法习得的表征与轮毂位置特征相结合，共同完成车辆分类任务。特别地，在分类器训练过程中，我们采用随机轮毂掩码策略对先前习得的表征进行微调，使其与轮毂位置特征协同优化。实验表明，与我们轮毂掩码策略相契合的data2vec蒸馏表征性能优于DINO方法，在联邦公路管理局定义的13类车辆分类任务中，实现了高达97.2%的Top-1分类准确率。