非表示:
キーワード:
Computer Science, Computer Vision and Pattern Recognition, cs.CV
要旨:
Beyond the success in classification, neural networks have recently shown
strong results on pixel-wise prediction tasks like image semantic segmentation
on RGBD data. However, the commonly used deconvolutional layers for upsampling
intermediate representations to the full-resolution output still show different
failure modes, like imprecise segmentation boundaries and label mistakes in
particular on large, weakly textured objects (e.g. fridge, whiteboard, door).
We attribute these errors in part to the rigid way, current network aggregate
information, that can be either too local (missing context) or too global
(inaccurate boundaries). Therefore we propose a data-driven pooling layer that
integrates with fully convolutional architectures and utilizes boundary
detection from RGBD image segmentation approaches. We extend our approach to
leverage region-level correspondences across images with an additional temporal
pooling stage. We evaluate our approach on the NYU-Depth-V2 dataset comprised
of indoor RGBD video sequences and compare it to various state-of-the-art
baselines. Besides a general improvement over the state-of-the-art, our
approach shows particularly good results in terms of accuracy of the predicted
boundaries and in segmenting previously problematic classes.