Object Detection with Discriminatively Trained Part Based Models

By Pedro F. Felzenszwalb, Ross B. Girshick, David A. McAllester, Deva Ramanan. 2010

10,728 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015, methodology): “The second way is usually adopted jointly with the first way [8].”
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model (2015, positive): “We use hard negative mining the same way as in [10, 8].”
Fast R-CNN (2015, background): “In [23], Zhu et al . studied this issue in depth for DPMs [7] and found that they saturate after only a few hundred to thousand training examples.”
Object Detection Networks on Convolutional Feature Maps (2015, methodology): “These hybrid approaches outperform their HOG- 28 based counterparts [2], [3], but still lag far behind R- 29 CNN, even when the hybrid model is trained end- 30 to-end [10].”
ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “1 8 O lg a R u ssa k o v sk y * et a l. ILSVRC 2013 Codename CLS LOC DET Insitutions Contributors and references Adobe 15.2 - - Adobe†, University of Illinois at Urbana-Champaign‡ Hailin Jin†, Zhe Lin†, Jianchao Yang†, Tom Paine‡ (Krizhevsky et al., 2012) AHoward 13.6 - - Andrew Howard Consulting An”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, background): “Since the analysis is best absorbed in the context of the associated plots, we present the discussion within the captions of Figure 5 and Figure 6.”
Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS) (2014, positive): “Large-scale object detection with DPM: Deformable Part Model (DPM) based representation of images is the state-of-the-art in object detection tasks [8].”
Relation Networks for Object Detection (2017, methodology): “For example, co-occurrence , which indicates how likely two object classes can exist in a same image, is used by DPM [15] to reﬁne object scores.”
Measuring Robustness to Natural Distribution Shifts in Image Classification (2020, methodology): “[30] Felzenszwalb, P.”
Natural Adversarial Examples (2019, methodology): “sculptures, toys, origami, embroidery, and so on, but we avoid such examples and only keep natural images during adversarial ﬁltration. While computer vision models such as the deformable parts model [11] more explicitly represented part conﬁgurations, current convolutional neural networks may produ”
Webly Supervised Learning of Convolutional Networks (2015, background): “The resulting clean data has helped signiﬁcantly advance performance on relevant tasks [15, 25, 19, 62].”
Feature Pyramid Networks for Object Detection (2016, methodology): “They were so critical that object detectors like DPM [7] required dense scale sampling to achieve good results (e.”
Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, methodology): “This has some similarity to boostrapping methods commonly used to assemble datasets for object detection [13], [53].”
Learning Non-maximum Suppression (2017, background): “This last stage is commonly referred to as “non-maximum suppression” (NMS) [10, 9, 21, 7, 20, 16].”
Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “Since then, greedy NMS has been the de-facto algorithm use in object det ction [8, 10, 24, 16].”
DeepSetNet: Predicting Sets with Deep Neural Networks (2016, background): “Traditional approaches follow the slidingwindow paradigm [44, 7, 46, 11, 2], where each possible (or rather plausible) image region is scored independently to contain a person or not.”