2018/05/19 by Yun Liu, Liu, Yun, Yujun Shi +9
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Digital Image Processing Techniques #FOS: Computer and information sciences #Retinal Imaging and Analysis #Visual Attention and Saliency Detection
paper · pdf · doi:10.48550/arxiv.1805.07548
openalex publication_date 2018/05/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation. To solve this fundamental issue, we consider a new challenging vision task, Internetly supervised semantic segmentation, which only uses Internet data with noisy image-level supervision of corresponding query keywords for segmentation model training. We address this task by proposing the following solution. A class-specific attention model unifying multiscale forward and backward convolutional features is proposed to provide initial segmentation "ground truth". The model trained with such noisy annotations is then improved by an online fine-tuning procedure. It achieves state-of-the-art performance under the weakly-supervised setting on PASCAL VOC2012 dataset. The proposed framework also paves a new way towards learning from the Internet without human interaction and could serve as a strong baseline therein. Code and data will be released upon the paper acceptance.