Towards Unified Object Detection and Semantic Segmentation

By Jian Dong, Qiang Chen, Shuicheng Yan, Alan L. Yuille. 2014

74 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

Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model (2015, neutral): “The motivation for this comes by the close connection between segmentation and detection and by the fact that segmentation related cues are empirically known to often help object detection [5, 11, 23].”
You Only Look Once: Unified, Real-Time Object Detection (2015, neutral): “2 NUS NIN C2000 [7] 63.”
Hypercolumns for object segmentation and fine-grained localization (2014, methodology): “[13] combine object detections from DPM [16] with semantic segmentation outputs from O2P [9] to improve both systems.”
Conditional Random Fields as Recurrent Neural Networks (2015, neutral): “NUS-UDS [16] n/a n/a 50.”
segDeepM: Exploiting segmentation and context in deep neural networks for object detection (2015, background): “In [6], the authors extended segDPM to incorporate segmentation compatibility also at the part level.”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, background): “Another uprising trend that is worth mentioning is the application of the object region proposals [131], [132], [160].”
Semantic object segmentation via detection in weakly labeled video (2015, background): “Detectionbased approaches have been widely studied on image segmentation [16, 31, 14, 7, 17, 26, 32].”
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].”
Contextual Priming and Feedback for Faster R-CNN (2016, background): “In fact, there has been a lot of interest in using segmentation in tandem with detection [30, 31, 37, 38]; e.”