Distributed Iterative Gating Networks for Semantic Segmentation
This work addresses pixel-wise labeling challenges in computer vision, offering an incremental improvement in recurrent network designs for semantic segmentation.
The paper tackles the problem of controlling information flow in neural networks for semantic segmentation by introducing Distributed Iterative Gating (DIGNet), a lightweight feedback routing mechanism that improves performance over feed-forward and other recurrent models on datasets like PASCAL VOC 2012, COCO-Stuff, and ADE20K.
In this paper, we present a canonical structure for controlling information flow in neural networks with an efficient feedback routing mechanism based on a strategy of Distributed Iterative Gating (DIGNet). The structure of this mechanism derives from a strong conceptual foundation and presents a light-weight mechanism for adaptive control of computation similar to recurrent convolutional neural networks by integrating feedback signals with a feed-forward architecture. In contrast to other RNN formulations, DIGNet generates feedback signals in a cascaded manner that implicitly carries information from all the layers above. This cascaded feedback propagation by means of the propagator gates is found to be more effective compared to other feedback mechanisms that use feedback from the output of either the corresponding stage or from the previous stage. Experiments reveal the high degree of capability that this recurrent approach with cascaded feedback presents over feed-forward baselines and other recurrent models for pixel-wise labeling problems on three challenging datasets, PASCAL VOC 2012, COCO-Stuff, and ADE20K.