Depth Adaptive Deep Neural Network for Semantic Segmentation
share
In this work, we present the depth-adaptive deep neural network using a depth map for semantic segmentation. Typical deep neural networks receive inputs at the predetermined locations regardless of the distance from the camera. This fixed receptive field presents a challenge to generalize the features of objects at various distances in neural networks. Specifically, the predetermined receptive fields are too small at a short distance, and vice versa. To overcome this challenge, we develop a neural network which is able to adapt the receptive field not only for each layer but also for each neuron at spatial locations. To adjust the receptive field, we propose the adaptive perception neuron and the in-layer multiscale neuron. The adaptive perception neuron is to adjust the receptive field at each spatial location using the corresponding depth information. The in-layer multiscale neuron is to apply the different size of the receptive field at each feature space to learn features at multiple scales. By the combination of these neurons, we propose the three fully convolutional neural networks. We demonstrate the effectiveness of the proposed neural networks on the novel hand segmentation dataset for hand-object interaction and publicly available RGB-D dataset for semantic segmentation. The experimental results show that the proposed method outperforms the state-of-the-art methods without any additional layers or pre/post-processing.
READ FULL TEXT