English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In this paper, we propose a noise-aware encoder-decoder framework todisentangle a clean saliency predictor from noisy training examples, where thenoisy labels are generated by unsupervised handcrafted feature-based methods.The proposed model consists of two sub-models parameterized by neural networks:(1) a saliency predictor that maps input images to clean saliency maps, and (2)a noise generator, which is a latent variable model that produces noises fromGaussian latent vectors. The whole model that represents noisy labels is a sumof the two sub-models. The goal of training the model is to estimate theparameters of both sub-models, and simultaneously infer the correspondinglatent vector of each noisy label. We propose to train the model by using analternating back-propagation (ABP) algorithm, which alternates the followingtwo steps: (1) learning back-propagation for estimating the parameters of twosub-models by gradient ascent, and (2) inferential back-propagation forinferring the latent vectors of training noisy examples by Langevin Dynamics.To prevent the network from converging to trivial solutions, we utilize anedge-aware smoothness loss to regularize hidden saliency maps to have similarstructures as their corresponding images. Experimental results on severalbenchmark datasets indicate the effectiveness of the proposed model.

Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection