A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation
This addresses the challenge of noisy label sets in multi-label image classification for computer vision applications, representing an incremental advance by introducing a deep learning approach to an existing problem.
The paper tackles the partial multi-label image classification problem, where images have multiple relevant labels mixed with noisy ones, by proposing a deep model with curriculum-based disambiguation and consistency regularization, achieving significant performance improvements over state-of-the-art methods on benchmark datasets.
In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels and other noisy labels. Existing PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions, which unfortunately is unavailable in many real tasks. Furthermore, because the objective function for disambiguation is usually elaborately designed on the whole training set, it can be hardly optimized in a deep model with SGD on mini-batches. In this paper, for the first time we propose a deep model for PML to enhance the representation and discrimination ability. On one hand, we propose a novel curriculum based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different classes. On the other hand, a consistency regularization is introduced for model retraining to balance fitting identified easy labels and exploiting potential relevant labels. Extensive experimental results on the commonly used benchmark datasets show the proposed method significantly outperforms the SOTA methods.