Adaptive Affinity Fields for Semantic Segmentation
arXiv:1803.10335
Abstract
Semantic segmentation has made much progress with increasingly powerful pixel-wise classifiers and incorporating structural priors via Conditional Random Fields (CRF) or Generative Adversarial Networks (GAN). We propose a simpler alternative that learns to verify the spatial structure of segmentation during training only. Unlike existing approaches that enforce semantic labels on individual pixels and match labels between neighbouring pixels, we propose the concept of Adaptive Affinity Fields (AAF) to capture and match the semantic relations between neighbouring pixels in the label space. We use adversarial learning to select the optimal affinity field size for each semantic category. It is formulated as a minimax problem, optimizing our segmentation neural network in a best worst-case learning scenario. AAF is versatile for representing structures as a collection of pixel-centric relations, easier to train than GAN and more efficient than CRF without run-time inference. Our extensive evaluations on PASCAL VOC 2012, Cityscapes, and GTA5 datasets demonstrate its above-par segmentation performance and robust generalization across domains.
arXiv commentTo appear in European Conference on Computer Vision (ECCV) 2018
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Learning Deconvolution Network for Semantic Segmentation
- Semantic Segmentation using Adversarial Networks
- Semantic Image Segmentation via Deep Parsing Network
- Playing for Data: Ground Truth from Computer Games
- High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks