Scene Parsing with Object Instances and Occlusion Ordering

By Joseph Tighe, Marc Niethammer, Svetlana Lazebnik. 2014

142 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

Panoptic Feature Pyramid Networks (2019, background): “Panoptic segmentation: The joint task of thing and stuff segmentation has a rich history, including early work on scene parsing [51], image parsing [52], and holistic scene understanding [56].”
Panoptic Segmentation (2018, methodology): “Interestingly, while semantic and instance segmentation dominate current work, in the pre-deep learning era there was interest in the joint task described using various names such as scene parsing [42], image parsing [43], or holistic scene understanding [50].”
Recurrent Instance Segmentation (2015, background): “In this section we summarize the main developments in these areas.”
Shape-aware Instance Segmentation (2016, methodology): “The early instances of this approach [29, 15] typically used pre-trained class-speciﬁc object detectors.”
COCO-Stuff: Thing and Stuff Classes in Context (2016, background): “Is stuff easier than things? Several works found that stuff is easier to segment than things [50, 28, 36, 51, 53, 62, 60, 63].”
OneFormer: One Transformer to Rule Universal Image Segmentation (2022, methodology): “The concept of universal image segmentation has existed for some time, starting with image and scene parsing [47, 48, 58], followed by panoptic segmentation as an effort to unify semantic and instance segmentation [29].”
Learning Rich Features from RGB-D Images for Object Detection and Segmentation (2014, methodology): “In this section, we study the task of instance segmentation as proposed in [19,36].”
Proposal-Free Network for Instance-Level Object Segmentation (2015, neutral): “Other works have resorted to the object detection task to initialize the instance segmentation and the complex post-processing such as integer quadratic program [34] and probabilistic model [38] to further determine the instance segments.”
Monocular Object Instance Segmentation and Depth Ordering with CNNs (2015, methodology): “Most related to our work are [36, 16, 39] which explicitly reason about class and instance segmentations as well as depth ordering.”
Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling (2016, methodology): “In [30], pixel-level semantic labels are used to score object candidates and vice versa in an alternating fashion, while also reasoning about occlusions and scene geometry.”
Learning to Fuse Things and Stuff (2018, background): “This seminal paper inspired a fertile research direction, including contributions on how to explicitly model the relations between things and stuff categories [34, 41, 37, 36, 26].”
Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs (2015, methodology): “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].”
Semantic Instance Segmentation with a Discriminative Loss Function (2017, background): “Two earlier works [43, 36] also use depth information to segment instances.”
MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation (2020, methodology): “This problem has further been studied using graphical models [41], [42], [43].”
MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation (2022, methodology): “This problem has further been studied using graphical models [41], [42], [43].”
Amodal Instance Segmentation (2016, methodology): “Earlier approaches rely on DPM [11] detections and predict segmentation masks using a simple appearance model [36,30,8], combine DPM detections and semantic segmentation predictions [12,9] or adopt a transductive approach [34].”
Towards Bounding-Box Free Panoptic Segmentation (2020, background): “scene segmentation together with individual instances of objects present in the scene. Historically this has been explored under different umbrella terms of scene understanding [43] and scene parsing [37]. In [17], Kirillov et al. coined the term and gave a more concrete deﬁ- nition by including For”
Semi-convolutional Operators for Instance Segmentation (2018, background): “Among other approaches using a clustering component, [49] leverages a coverage loss and [55,50,51] make use of depth information.”