Multilabel classification outperforms detection-based technique

In real-life scenarios, an input image typically comprises multiple objects, and their classification is often implemented using detection-based classification (DBC). In this approach, objects are first detected and then identified individually using a deep architecture. In this study, we demonstrate that the accuracy achieved by multilabel classification (MLC) surpasses that of DBC for a relatively small number of multilabel learning combinations. The crossover point at which DBC maximizes accuracy depends on the type of multilabel images, such as the number of multiple objects per image. The results are based on VGG-6 trained on the CIFAR-100 dataset using an upper bound for DBC accuracy, assumed under perfect detection conditions. Furthermore, we briefly discuss the potential relevance of these findings to advanced communication theory and natural language processing. The results suggest a need to reexamine the advantages of MLC over DBC using more complex datasets and deep architectures.