POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation

By Thomas Berg, Peter N. Belhumeur. 2013

404 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Developmental Biology, Ecology, Molecular Biology

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

In Developmental Biology

In Ecology

In Molecular Biology

Citations in the corpus

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition (2013, background): “It also outperforms POOF (Berg & Belhumeur, 2013), which is the best part-based approach for ﬁne-grained categorization published so far.”
Deep Learning Face Attributes in the Wild (2014, background): “We also report performance on 19 extended attributes and compare our result with [14] and [2].”
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition (2014, methodology): “Finally, POOF [5] adopts several discriminative learners for the same parts from each two different subcategories.”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, background): “[7] learned a set of highly discriminative intermediate features by learning a descriptor for each pair of keypoints.”
The application of two-level attention models in deep convolutional neural network for fine-grained image classification (2014, background): “The strongest supervised setting is using bounding box and part landmarks in both training and testing phase, which is often used to test performance upbound [2].”
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, background): “The majority of research in fine-grained recognition has focused on developing improved models for classification [2, 5, 7, 15, 17, 18, 24, 30, 37, 44, 45, 58, 59, 60, 63, 64].”
Deep Image: Scaling up Image Recognition (2015, neutral): “ery [44] 81.0 Ours 84.9 GMTL [38] √ √ 44.2 Symbiotic [6] √ √ 59.4 Alignments [17] √ √ 67.0 B-CNN (D,M) [30] √ 81.9 Ours+BBox √ 85.6 PB R-CNN [52] √ √ 73.9 PN-DCN [4] √ √ 75.7 DPD [53] √ √ √ 51.0 POOF [3] √ √ √ 56.8 Nonparametric [18] √ √ √ 57.8 Symbiotic [6] √ √ √ 61.0 DPD+DeCAF [16] √ √ √ 65.0 PB R”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, background): “[4] learns a linear classiﬁer for each pair of parts and classes.”
P-CNN: Pose-Based CNN Features for Action Recognition (2015, background): “Examples include alignment of faces for face recognition [2] as well as alignment of body parts for recognizing species of birds [12].”
The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “Most ﬁne-grained research papers present a novel model for classiﬁcation [4, 6, 7, 12, 15, 17, 25, 31, 40, 45, 46, 57, 58, 59, 61, 62].”
Part Detector Discovery in Deep Convolutional Neural Networks (2014, neutral): “Object representations for visual recognition are often part-based [8,9] and in several cases information about semantic parts is given.”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, methodology): “Applications include distinguishing different types of flowers [36, 37], plants [2, 29], insects [30, 35], birds [5, 10, 15, 19, 31, 43, 50, 51], dogs [27, 33, 38, 39], vehicles [42], shoes [4], or architectural styles [34].”
Fisher and VLAD with FLAIR (2014, methodology): “As a result, without any further knowledge of the birds [30], their pose [32] or location [2] we obtain an accuracy of 55.”
Local Alignments for Fine-Grained Categorization (2014, background): “Recent works in computer vision have veri-ﬁed this mechanism (Farrell et al. 2011; Zhang et al. 2012; Chai et al. 2013; Zhang et al. 2013; Berg and Belhumeur 2013).”
Picking Deep Filter Responses for Fine-Grained Image Recognition (2016, background): “Among them the strongest supervised setting is to use both object and part level annotations [1], [17], [28].”
Learning to Navigate for Fine-grained Classification (2018, background): “Some previous works [45,8,3,46,13,2,29] take advantage of fine-grained human annotations, like annotations for bird parts in bird classification.”
Labeled Faces in the Wild: A Survey (2016, neutral): “Tom-vs-Pete, 2012 [16], POOF, 2013 [17].”
Leveraging Visual Question Answering for Image-Caption Ranking (2016, background): “Previous works have explored the use of attributes [10,11,12], parts [13,14], poselets [15,16], objects [17], actions [18] and contextual information [19,20,21] as sematic mid-level representations for visual recognition.”