SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networks. (arXiv:2112.03731v2 [cs.CV] UPDATED)

Feed-forward only convolutional neural networks (CNNs) may ignore intrinsic
relationships and potential benefits of feedback connections in vision tasks
such as saliency detection, despite their significant representation
capabilities. In this work, we propose a feedback-recursive convolutional
framework (SalFBNet) for saliency detection. The proposed feedback model can
learn abundant contextual representations by bridging a recursive pathway from
higher-level feature blocks to low-level layer. Moreover, we create a
large-scale Pseudo-Saliency dataset to alleviate the problem of data deficiency
in saliency detection. We …

arxiv cv distribution learning networks