We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder. Furthermore, to allow maximal adaptivity, the weights at each decoder block vary spatially. For this purpose, we design a new type of hypernetwork, composed of a nested U-Net for drawing higher level context features, a multi-headed weight generating module which generates the weights of each block in the decoder immediately before they are consumed, for efficient memory utilization, and a primary network that is composed of novel dynamic patch-wise convolutions. Despite the usage of less-conventional blocks, our architecture obtains real-time performance. In terms of the runtime vs. accuracy trade-off, we surpass state of the art (SotA) results on popular semantic segmentation benchmarks: PASCAL VOC 2012 (val. set) and real-time semantic segmentation on Cityscapes, and CamVid. The code is available: https://nirkin.com/hyperseg.
|Title of host publication||Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021|
|Publisher||IEEE Computer Society|
|Number of pages||10|
|State||Published - 2021|
|Event||2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States|
Duration: 19 Jun 2021 → 25 Jun 2021
|Name||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Conference||2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021|
|Period||19/06/21 → 25/06/21|
Bibliographical noteFunding Information:
Performed this work while an intern at Facebook.
© 2021 IEEE