Semi-supervised Active Salient Object Detection
作者：
Highlights：
• We design a saliency encoder-decoder with adversarial discriminator to generate a confidence map, representing the network uncertainty on the current prediction. We then select the least confident (discriminative) samples from the unlabeled pool to form the “candidate labeled pool”.
• We train a Variational Auto-Encoder (VAE) to select and add the most representative data from the “candidate labeled pool” into the labeled pool by comparing their corresponding features in the latent space. Within our frame-work, these two networks are optimized conditioned on the states of each other progressively.
摘要
•We design a saliency encoder-decoder with adversarial discriminator to generate a confidence map, representing the network uncertainty on the current prediction. We then select the least confident (discriminative) samples from the unlabeled pool to form the “candidate labeled pool”.•We train a Variational Auto-Encoder (VAE) to select and add the most representative data from the “candidate labeled pool” into the labeled pool by comparing their corresponding features in the latent space. Within our frame-work, these two networks are optimized conditioned on the states of each other progressively.
论文关键词：Salient object detection,Annotation-efficient Learning,Active learning,Variational Auto-Encoder
论文评审过程：Received 15 January 2021, Revised 17 September 2021, Accepted 3 October 2021, Available online 9 October 2021, Version of Record 16 October 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108364
