Semi-supervised Ranking for Object Image Blur Assessment
This work addresses the challenge of blur assessment for object recognition and retrieval, but it is incremental as it builds on existing ranking and semi-supervised methods.
The paper tackled the problem of assessing blurriness in object images by addressing the lack of reliable labels and effective learning strategies, proposing a semi-supervised framework that uses pairwise rank labels and quadruplet ranking consistency, resulting in demonstrated effectiveness in experiments.
Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning strategies. Current datasets are labeled with limited and confused quality levels. To overcome this limitation, we propose to label the rank relationships between pairwise images rather their quality levels, since it is much easier for humans to label, and establish a large-scale realistic face image blur assessment dataset with reliable labels. Based on this dataset, we propose a method to obtain the blur scores only with the pairwise rank labels as supervision. Moreover, to further improve the performance, we propose a self-supervised method based on quadruplet ranking consistency to leverage the unlabeled data more effectively. The supervised and self-supervised methods constitute a final semi-supervised learning framework, which can be trained end-to-end. Experimental results demonstrate the effectiveness of our method.