Template-Based Automatic Search of Compact Semantic Segmentation Architectures

  title={Template-Based Automatic Search of Compact Semantic Segmentation Architectures},
  author={Vladimir Nekrasov and Chunhua Shen and Ian D. Reid},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
Automatic search of neural architectures for various vision and natural language tasks is becoming a prominent tool as it allows to discover high-performing structures on any dataset of interest. Nevertheless, on more difficult domains, such as dense per-pixel classification, current automatic approaches are limited in their scope – due to their strong reliance on existing image classifiers they tend to search only for a handful of additional layers with discovered architectures still… Expand
Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
This paper provides a literature review on NAS, in particular the weight-sharing methods, and points out that the major challenge comes from the optimization gap between the super-network and the sub-architectures. Expand
ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation
A fewparameter compact Bayesian convolutional architecture is demonstrated, that achieves a marginal improvement in accuracy in comparison to related work using significantly fewer parameters and compute operations. Expand


Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
This work focuses on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks, and relies on a progressive strategy that terminates non-promising architectures from being further trained, and on Polyak averaging coupled with knowledge distillation to speed-up the convergence. Expand
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
This work constructs a recursive search space for meta-learning techniques for dense image prediction focused on the tasks of scene parsing, person-part segmentation, and semantic image segmentation and demonstrates that even with efficient random search, this architecture can outperform human-invented architectures. Expand
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
This paper presents a network level search space that includes many popular designs, and develops a formulation that allows efficient gradient-based architecture search and demonstrates the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Expand
Fully Convolutional Networks for Semantic Segmentation
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Expand
ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation
A deep architecture that is able to run in real time while providing accurate semantic segmentation, and a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy is proposed. Expand
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
This work proposes a novel ResNet-like architecture that exhibits strong localization and recognition performance, and combines multi-scale context with pixel-level accuracy by using two processing streams within the network. Expand
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner. Expand
Large-Scale Evolution of Image Classifiers
It is shown that it is now possible to evolve models with accuracies within the range of those published in the last year, starting from trivial initial conditions and reaching accuracies of 94.6% and 77.0%, respectively. Expand
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
A novel Bilateral Segmentation Network (BiSeNet) is proposed that makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Expand
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. Expand