Semantic part segmentation using compositional model combining shape and appearance

Wang, Yunlong; Yuille, Alan

doi:10.1109/cvpr.2015.7298788

Cited by 95 publications

(90 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method instead trains on silhouette input, allowing the use of synthetic training imagery. The related task of animal part segmentation [29,30] has seen some progress due to general object part datasets [31,32].…”

Section: Related Workmentioning

confidence: 99%

Creatures Great and SMAL: Recovering the Shape and Motion of Animals from Video

Biggs

Roddick

Fitzgibbon

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We present a system to recover the 3D shape and motion of a wide variety of quadrupeds from video. The system comprises a machine learning front-end which predicts candidate 2D joint positions, a discrete optimization which finds kinematically plausible joint correspondences, and an energy minimization stage which fits a detailed 3D model to the image. In order to overcome the limited availability of motion capture training data from animals, and the difficulty of generating realistic synthetic training images, the system is designed to work on silhouette data. The joint candidate predictor is trained on synthetically generated silhouette images, and at test time, deep learning methods or standard video segmentation tools are used to extract silhouettes from real data. The system is tested on animal videos from several species, and shows accurate reconstructions of 3D shape and pose.

show abstract

Section: Related Workmentioning

confidence: 99%

Creatures Great and SMAL: Recovering the Shape and Motion of Animals from Video

Biggs

Roddick

Fitzgibbon

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The task is to label each pixel according to whether this pixel belongs to one of the body parts (head, leg, tail, body). We split the dataset following [54] and obtain 294 training images and 227 test images. We compare the performance of our model with state-of-the art methods including the most recent method LG-LSTM [55].…”

Section: Horse-cow Parsing Datasetmentioning

confidence: 99%

Gated Feedback Refinement Network for Dense Image Labeling

Islam

Rochan

Bruce

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

190

144

View full text Add to dashboard Cite

Effective integration of local and global contextual information is crucial for semantic segmentation and dense image labeling. We develop two encoder-decoder based deep learning architectures to address this problem. We first propose a network architecture called Label Refinement Network (LRN) that predicts segmentation labels in a coarse-to-fine fashion at several spatial resolutions. In this network we also define loss functions at several stages to provide supervision at different stages of training. However, there are limits to the quality of refinement possible if ambiguous information is passed forward. In order to address this issue we also propose Gated Feedback Refinement Network (G-FRNet) that addresses this limitation. Initially, G-FRNet makes a coarse-grained prediction which it progressively refines to recover details by effectively integrating local and global contextual information during the refinement stages. This is achieved by gate units proposed in this work, that control information passed forward in order to resolve ambiguity. Experiments were conducted on four challenging dense labeling datasets (CamVid, PASCAL VOC 2012, Horse-Cow Parsing, PASCAL-Person-Part, and SUN-RGBD). G-FRNet achieves state-of-the-art semantic segmentation results on the CamVid and Horse-Cow Parsing datasets, and produces results competitive with the best performing approaches that appear in the literature for the other three datasets.

show abstract

“…However, the setting is typically tightly cropped bounding boxes of pedestrians, while we are interested in the completely unconstrained case. Wang and Yuille [48] use compositional models of parts to label parts of objects assuming a tightly cropped bounding box. Wang et al [49] consider an extension to CNN-based semantic segmentation where each pixel gets not only a category label but also a part label.…”

Section: Detection and Segmentationmentioning

confidence: 99%

Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns

Hariharan

Pont-Tuset

Girshick

et al. 2017

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a feature representation. However, the information in this layer may be too coarse spatially to allow precise localization. On the contrary, earlier layers may be precise in localization but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hypercolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation, where we improve state-of-the-art from 49.7 mean AP to 62.4, keypoint localization, where we get a 3.3 point boost over a strong regression baseline using CNN features, and part labeling, where we show a 6.6 point gain over a strong baseline.

show abstract

Semantic part segmentation using compositional model combining shape and appearance

Cited by 95 publications

References 33 publications

Creatures Great and SMAL: Recovering the Shape and Motion of Animals from Video

Creatures Great and SMAL: Recovering the Shape and Motion of Animals from Video

Gated Feedback Refinement Network for Dense Image Labeling

Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns

Contact Info

Product

Resources

About