Destroy the Robust Commercial Watermark via Deep Convolutional Encoder-Decoder Network

Nowadays, robust watermark is widely used to protect the copyright of multimedia. Robustness is the most important ability for watermark in application. Since the watermark attacking algorithm is a good way to promote the development of robust watermark, we proposed a new method focused on destroying the commercial watermark. At first, decorrelation and desynchronization are used as the preprocessing method. Considering that the train set of thousands of watermarked images is hard to get, we further use the Bernoulli sampling and dropout in network to achieve the training instance extension. The experiments show that the proposed network can effectively remove the commercial watermark. Meanwhile, the processed image can result in good quality that is almost as good as the original image.

Recovering Accurate Labeling Information from Partially Valid Data for Effective Multi-Label Learning

Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid. To address the noisy issue, the existing PML methods basically recover the ground-truth labels by leveraging the ground-truth confidence of the candidate label, i.e., the likelihood of a candidate label being a ground-truth one. However, they neglect the information from non-candidate labels, which potentially contributes to the ground-truth label recovery. In this paper, we propose to recover the ground-truth labels, i.e., estimating the ground-truth confidences, from the label enrichment, composed of the relevance degrees of candidate labels and irrelevance degrees of non-candidate labels. Upon this observation, we further develop a novel two-stage PML method, namely Partial Multi-Label Learning with Label Enrichment-Recovery (PML3ER), where in the first stage, it estimates the label enrichment with unconstrained label propagation, then jointly learns the ground-truth confidence and multi-label predictor given the label enrichment. Experimental results validate that PML3ER outperforms the state-of-the-art PML methods.