Top-Down Guided Fusion Network for Object Contour Detection

Object contours detected by existing methods are generally inaccurate,thick and contaminated by inner edges.A top-down guided fusion network(TDGF-Net)is proposed for object contour detection.Firstly,TDGF-Net extracts multi-level features using popular convolutional neural network architectures.Secondly,considering that edges in lower levels of features are more precise but contain noisy edges,while higher levels of features are more helpful to discriminate contours,TDGF-Net gradually fuses the multi-level features in a top-down manner and uses the features from the higher levels to enhance contours and suppress noises in the lower levels.Finally,an improved version of the binary cross entropy loss is presented to train the proposed network.The proposed network is experimentally compared with state-of-the-art methods based on the public SBD dataset in PyTorch.Qualitative and quantitative results show that compared to state-of-the-art methods,our network generates more accurate,thinner and cleaner contour edges.