An Exemplar-Based CRF for Multi-instance Object Segmentation

By Xuming He, Stephen Gould. 2014

54 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Shape-aware Instance Segmentation (2016, methodology): “The early instances of this approach [29, 15] typically used pre-trained class-speciﬁc object detectors.”
The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, methodology): “Following this line, [9, 37, 40, 63, 81] propose different approaches that combine the strengths of CNNs and Conditional Random Fields (CRFs).”
Finely-grained annotated datasets for image-based plant phenotyping (2016, methodology): “Task: Some approaches to multi-instance (or multi-label) segmentation rely on accurate boundary detection, which is used for example to initialize template-based models (He and Gould, 2014; Yin et al., 2014).”
Monocular Object Instance Segmentation and Depth Ordering with CNNs (2015, background): “However, we follow some of the recent work [10, 39, 36, 11, 37] and argue that the next generation of recognition techniques should provide a more detailed parsing of a scene by labeling each object instance in an image with an accurate segmentation, a generic class, and 3D information such as…”
Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs (2015, background): “While detection might have been a good proxy when performance was low, recent work has been trying to go beyond simple boxes by providing a detailed segmentation mask for each object instance [12, 30, 28, 13, 29].”
CliqueCNN: Deep Unsupervised Exemplar Learning (2016, methodology): “The exemplar paradigm has been successfully employed in diverse areas such as segmentation [11], grouping [10], instance retrieval [2, 19], and object recognition [15, 5].”
segmentation in plant phenotyping: a collation study. Machine Vision and Applications (2017, methodology): “Finally, graphical methods have also been applied to resolve and segment overlapping objects [26], and were tested also on datasets showing multiple horses.”
Leaf segmentation in plant phenotyping: a collation study (2015, methodology): “Finally, graphical methods have also been applied to resolve and segment overlapping objects [26], and were tested also on datasets showing multiple horses.”
SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation – A Synthetic Dataset and Baselines (2019, methodology): “Reference images are used in [39] and the approach is evaluated on the TUD Pedestrian [3] and the Polo dataset [107].”
Improving Semantic Segmentation via Decoupled Body and Edge Supervision (2020, methodology): “mpetitive scene parsing datasets and achieve top performance. 2 Related work Semantic segmentation. Recent approaches for semantic segmentation are predominantly based on FCNs [3]. Some earlier works [27,28,29,30,31,32] use 4 X. Li et al. structured prediction operators such as conditional random el”
Gated-SCNN: Gated Shape CNNs for Semantic Segmentation (2019, background): “Several works [9, 32, 59, 43, 20, 3, 36, 23, 5] propose to use structured prediction modules such as conditional random fields (CRFs) on network output for improving the segmentation performance, especially around object boundaries.”
Instance-Level Segmentation with Deep Densely Connected MRFs (2015, methodology): “In this paper, we formulate the global labeling problem with a novel densely connected Markov random field and show how to encode various intuitive potentials in a way that is amenable to efficient mean field inference [13].”
Annotated Image Datasets of Rosette Plants (2014, methodology): “We also do hope that this dataset and its future versions, would be used from the computer vision community to learn suitable image statistics [19], adapt and test counting algorithms with [20] and without temporal information [21, 22, 23], segmentation algorithms [24, 25, 26, 27, 28], multi-label s”
Boundary-Aware Instance Segmentation (2016, methodology): “The early instances of this approach [32, 16] typically used pre-trained class-speciﬁc object detectors.”
Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries (2015, background): “Joint Models in Vision A series of context models have leveraged MRFs in various vision tasks, such as image segmentation [16, 27, 33], object recognition [9, 26], object detection [46], pose and activity recognition [52] and other recognition tasks [20, 36].”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, background): “Recently, there are some works making efforts towards this direction by combining state-of-the-art detectors with the CRF modelling [115], [165], [166] which have achieved some progress.”