DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
Reads0
Chats0
TLDR
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.Abstract:
In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First , we highlight convolution with upsampled filters, or ‘atrous convolution’, as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second , we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third , we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed “DeepLab” system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7 percent mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.read more
Citations
More filters
Proceedings ArticleDOI
Pyramid Scene Parsing Network
TL;DR: This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.
Book ChapterDOI
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
TL;DR: 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.
Posted Content
YOLOv4: Optimal Speed and Accuracy of Object Detection
TL;DR: This work uses new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, C mBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100.
Proceedings ArticleDOI
Dual Attention Network for Scene Segmentation
TL;DR: New state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset is achieved without using coarse data.
Proceedings ArticleDOI
Deformable Convolutional Networks
TL;DR: Deformable convolutional networks as discussed by the authors augment the spatial sampling locations in the modules with additional offsets and learn the offsets from the target tasks, without additional supervision, which can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard backpropagation.
References
More filters
Book ChapterDOI
Instance-Sensitive Fully Convolutional Networks
TL;DR: In this paper, a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances, are computed and then a simple assembling module is able to output instance candidate at each position.
Journal ArticleDOI
Fast Approximate Energy Minimization with Label Costs
TL;DR: In this article, an extension of the?-expansion algorithm is proposed that optimizes label costs with well-characterized optimality bounds, which is useful for multi-model fitting.
Proceedings ArticleDOI
Material recognition in the wild with the Materials in Context Database
TL;DR: The Materials in Context Database (MINC) as mentioned in this paper is a large-scale, open dataset of materials in the wild, and combine this dataset with deep learning to achieve material recognition and segmentation of images from the wild.
Proceedings ArticleDOI
Convolutional feature masking for joint object and stuff segmentation
Jifeng Dai,Kaiming He,Jian Sun +2 more
TL;DR: Wang et al. as mentioned in this paper proposed to exploit shape information via masking convolutional features, where the proposal segments (e.g., super-pixels) are treated as masks on the CNN feature maps and used to train classifiers for recognition.
Proceedings ArticleDOI
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts
TL;DR: In this article, a fully connected model is proposed to arrange templates for the holistic object and body parts separately and then decouples the holistic objects or body parts from the model when they are hard to detect.