Learning Scene-Specific Pedestrian Detectors without Real Data

By Hironori Hattori, Vishnu Naresh Boddeti, Kris Kitani, Takeo Kanade, F. Felzenszwalb, Ross B. Girshick, D. McAllester, D. Ramanan. 2015

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

Recognition in Terra Incognita (2018, methodology): “[48,49,50,51,52] look at methods for adapting detectors from one data source to another, such as from synthetic to real data or from images to video.”
Geometric Image Synthesis (2018, methodology): “The task of the network is to learn the unknown parameters from the training data directly and apply them to generate images from new input geometry.”
Domain Adaptive Faster R-CNN for Object Detection in the Wild (2018, background): “There also exists work to learn detectors from alternative sources, such as from images to videos [54], from 3D models [46, 53], or from synthetic models [25].”
Autonomous Cars: Research Results, Issues, and Future Challenges (2019, methodology): “be used and if the data is not labeled, unsupervised learning can be used [53]–[55].”
MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild (2016, background): “In [11], a scene-speciﬁc pedestrian detectors was learned without real data while [9] synthesized virtual samples with a generative model to enhance the classiﬁcation performance of a discriminative model.”
UnrealCV: Connecting Computer Vision to Unreal Engine (2016, background): “Researchers have shown that training on synthetic images is helpful for real world tasks[18,16,11,14,21].”
Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars (2017, background): “…2016; Varol et al. 2017), depth prediction (Su et al. 2014), pedestrian detection (Marin et al. 2010; Pishchulin et al. 2011; Vázquez et al. 2014; Hattori et al. 2015), action recognition (Rahmani and Mian 2015, 2016; Roberto de et al. 2017), semantic segmentation (Richter et al. 2016), scene…”
Driving in the Matrix: Can virtual worlds replace human-generated annotations for real world tasks? (2016, background): “Further work inserted synthetic pedestrians at a variety of angles into real scenes to train a part-based model classiﬁer [14].”