• Corpus ID: 235358460

Multi-Exit Semantic Segmentation Networks

  title={Multi-Exit Semantic Segmentation Networks},
  author={Alexandros Kouris and Stylianos I. Venieris and Stefanos Laskaridis and Nicholas D. Lane},
Semantic segmentation arises as the backbone of many vision systems, spanning from self-driving cars and robot navigation to augmented reality and teleconferencing. Frequently operating under stringent latency constraints within a limited resource envelope, optimising for efficient execution becomes important. To this end, we propose a framework for converting state-of-the-art segmentation models to MESS networks; specially trained CNNs that employ parametrised early exits along their depth to… 
Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
This paper decomposes the design methodology of early-exit networks to its key components and surveys the recent advances in each one of them, positioning early-exiting against other efficient inference solutions and providing insights on the current challenges and most promising future directions for research in the field.
DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device
DynO is presented, a distributed inference framework that combines the best of both worlds to address several challenges, such as device heterogeneity, varying bandwidth and multi-objective requirements, and outperforms the current state-of-the-art.
How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures
Preliminary answers to this potentially game-changing question are provided by presenting an array of design techniques for efficient AI systems by examining the major roadblocks when targeting both programmable processors and custom accelerators.
OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devices
Radical progress in the field of deep learning (DL) has led to unprecedented accuracy in diverse inference tasks. As such, deploying DL models across mobile platforms is vital to enable the


Learning Dynamic Routing for Semantic Segmentation
  • Yanwei Li, Lin Song, Jian Sun
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
A conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing, which generates data-dependent routes, adapting to the scale distribution of each image, and compares with several static architectures, which can be modeled as special cases in the routing space.
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.
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.
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.
A Comparative Study of Real-Time Semantic Segmentation for Autonomous Driving
A real-time segmentation benchmarking framework and study various segmentation algorithms for autonomous driving and a generic meta-architecture via a decoupled design where different types of encoders and decoders can be plugged in independently.
SemanticFusion: Dense 3D semantic mapping with convolutional neural networks
This work combines Convolutional Neural Networks (CNNs) and a state-of-the-art dense Simultaneous Localization and Mapping (SLAM) system, ElasticFusion, which provides long-term dense correspondences between frames of indoor RGB-D video even during loopy scanning trajectories, and produces a useful semantic 3D map.
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.
Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network
This work proposes a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation and suggests a residual-based boundary refinement to further refine the object boundaries.
HAPI: Hardware-Aware Progressive Inference
This work presents HAPI, a novel methodology for generating highperformance early-exit networks by co-optimising the placement of intermediate exits together with the early- exit strategy at inference time, and proposes an efficient design space exploration algorithm which enables the faster traversal of a large number of alternative architectures and generates the highest-performing design.
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.