Highly Efficient Salient Object Detection with 100K Parameters
- a flexible convolutional module, namely gOctConv, to efficiently utilize both in-stage and cross-stages multi-scale features for SOD task, while reducing the representation redundancy by a novel dynamic weight decay scheme.
- we build an extremely light-weighted SOD model, namely CSNet–achieves comparable performance with ∼ 0.2% parameters
Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton
1.a dynamic feature integration strategy to explore the feature combinations automatically according to each input and task, and solve three contrasting tasks simultaneously in an end-to-end unified framework