Gated Feedback Refinement Network for Dense Image Labeling
01 Jul 2017-pp 4877-4885
TL;DR: This paper proposes Gated Feedback Refinement Network (G-FRNet), an end-to-end deep learning framework for dense labeling tasks that addresses this limitation of existing methods and introduces gate units that control the information passed forward in order to filter out ambiguity.
Abstract: Effective integration of local and global contextual information is crucial for dense labeling problems. Most existing methods based on an encoder-decoder architecture simply concatenate features from earlier layers to obtain higher-frequency details in the refinement stages. However, there are limits to the quality of refinement possible if ambiguous information is passed forward. In this paper we propose Gated Feedback Refinement Network (G-FRNet), an end-to-end deep learning framework for dense labeling tasks that addresses this limitation of existing methods. Initially, G-FRNet makes a coarse prediction and then it progressively refines the details by efficiently integrating local and global contextual information during the refinement stages. We introduce gate units that control the information passed forward in order to filter out ambiguity. Experiments on three challenging dense labeling datasets (CamVid, PASCAL VOC 2012, and Horse-Cow Parsing) show the effectiveness of our method. Our proposed approach achieves state-of-the-art results on the CamVid and Horse-Cow Parsing datasets, and produces competitive results on the PASCAL VOC 2012 dataset.
Citations
More filters
08 Sep 2018
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.
Abstract: Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89% and 82.1% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at https://github.com/tensorflow/models/tree/master/research/deeplab.
7,113 citations
Cites methods from "Gated Feedback Refinement Network f..."
...Encoder-decoder: The encoder-decoder networks have been successfully applied to many computer vision tasks, including human pose estimation [53], object detection [45, 66, 19], and semantic segmentation [49, 54, 61, 3, 43, 59, 57, 33, 76, 20]....
[...]
Posted Content•
TL;DR: The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
Abstract: In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
5,691 citations
Cites background or methods from "Gated Feedback Refinement Network f..."
...Second, the encoder-decoder structure [3, 61, 20, 45, 60, 58, 33] exploits multi-scale features from the encoder part and recovers the spatial resolution from the decoder part....
[...]
...More recently, RefineNet [45] and [60, 58, 33] have demonstrated the effectiveness of models based on encoder-decoder structure on several semantic segmentation benchmarks....
[...]
14 Jun 2020
TL;DR: EfficientDetD7 as discussed by the authors proposes a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multi-scale feature fusion, and a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time.
Abstract: Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multi-scale feature fusion; Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and EfficientNet backbones, we have developed a new family of object detectors, called EfficientDet, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single-model and single-scale, our EfficientDetD7 achieves state-of-the-art 52.2 AP on COCO test-dev with 52M parameters and 325B FLOPs, being 4x – 9x smaller and using 13x – 42x fewer FLOPs than previous detector.
3,423 citations
Posted Content•
TL;DR: The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.
Abstract: High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams \emph{in parallel}; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at~{\url{this https URL}}.
1,278 citations
Cites background from "Gated Feedback Refinement Network f..."
...Other works include: light upsample process [7], [24], [92], [152], possibly with dilated convolutions used in the backbone [63], [89], [113]; light downsample and heavy upsample processes [141], recombinator networks [55]; improving skip connections with more or complicated convolutional units [64], [111], [180], as well as sending information from low-resolution skip connections to highresolution skip connections [189] or exchanging information between them [49]; studying the details of the upsample process [147]; combining multi-scale pyramid representations [22], [154]; stacking multiple DeconvNets/UNets/Hourglass [44], [149] with dense connections [135]....
[...]
TL;DR: The High-Resolution Network (HRNet) as mentioned in this paper maintains high-resolution representations through the whole process by connecting the high-to-low resolution convolution streams in parallel and repeatedly exchanging the information across resolutions.
Abstract: High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet .
1,162 citations
References
More filters
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Abstract: Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.
28,225 citations
"Gated Feedback Refinement Network f..." refers background or methods in this paper
...LRN [14] achieves 64.2% mean IoU which outperforms FCN [21] and SegNet [1]....
[...]
...Following prior work [3, 21, 1], we augment the training set with extra labeled PASCAL VOC images from [11]....
[...]
...Other approaches which use refinement process straight away combines convolution features (using skip connections [21]) with coarse label maps through concatenation to generate a new label map....
[...]
...0% mean IoU accuracy compared to encoderdecoder based architecture ([22, 31, 21])....
[...]
...Following [22, 3, 21], we add two convolution layers conv6 and conv7 at the end of encoder....
[...]
TL;DR: The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.
Abstract: The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection.
This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.
15,935 citations
"Gated Feedback Refinement Network f..." refers background or methods in this paper
...PASCAL VOC 2012 [8] is a challenging dataset for semantic segmentation....
[...]
...This dataset contains images of horse and cow images only, which are manually selected from the PASCAL VOC 2010 benchmark [8] based on most observable instances....
[...]
17 Jul 1986
15,313 citations
TL;DR: Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet.
Abstract: We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network [1] . The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN [2] and also with the well known DeepLab-LargeFOV [3] , DeconvNet [4] architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures and can be trained end-to-end using stochastic gradient descent. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. These quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at http://mi.eng.cam.ac.uk/projects/segnet/ .
13,468 citations
"Gated Feedback Refinement Network f..." refers background or methods in this paper
...LRN [14] achieves 64.2% mean IoU which outperforms FCN [21] and SegNet [1]....
[...]
...Our G-FRNet is inspired by the encoder-decoder architecture [22, 1, 14] for dense image labeling....
[...]
...Following prior work [3, 21, 1], we augment the training set with extra labeled PASCAL VOC images from [11]....
[...]
...However, there are only few recent methods [22, 1] that use a simpler encoder-decoder architecture for this problem, and it is most natural to compare our approach directly with this related family of models....
[...]
...LRN [14] outperforms SegNet [1] by more than 11% (in terms of mean IoU) while our approach (i....
[...]