Understanding Objects in Detail with Fine-Grained Attributes

By Andrea Vedaldi, Siddharth Mahendran, Stavros Tsogkas, Subhransu Maji, Ross B. Girshick, Juho Kannala, Esa Rahtu, Iasonas Kokkinos, Matthew B. Blaschko, David J. Weiss and 4 more. 2014

119 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

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, background): “Considerable work has also gone into the challenging task of curating finegrained datasets [4,58,27,30,31,59,65,60,70] and developing interactive methods for recognition with a human in the loop [6,62,61,63].”
Bilinear CNN Models for Fine-Grained Visual Recognition (2015, background): “Index Terms—Fine-grained recognition, Texture recognition, Bilinear models, Convolutional Neural Networks, Visualization F”
The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “The vision community has released many ﬁne-grained datasets covering several domains such as birds [5, 50, 52, 56], dogs [23, 34], airplanes [36, 51], ﬂowers [37], leaves [28], trees [55] and cars[24, 32].”
The iNaturalist Challenge 2017 Dataset (2017, background): “The vision community has released many fine-grained datasets covering several domains such as birds [42, 40, 2, 38, 16], dogs [14, 28, 22], airplanes [23, 39], flowers [26], leaves [18], trees [41] and cars [17, 20, 46, 6].”
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning (2018, background): “Beyond pixels, we also leverage other information including parts [66, 7, 67], attributes [57, 18], human interactions [8, 13] and text descriptions [42, 22].”
Multi-Task CNN Model for Attribute Prediction (2015, methodology): “While most of the existing methods train independent classifiers to predict attributes [13], [30], [55], typical statistical models, like naive Bayesian and structured SVM models, are used to address the problem.”
Do Semantic Parts Emerge in Convolutional Neural Networks? (2016, background): “The most notable examples of works on semantic part models are ﬁne-grained recognition [8,9,10], generic object detection [5], articulated pose estimation [11,12,13], and attribute prediction [14,15,16].”
Understanding Neural Networks through Representation Erasure (2016, methodology): “Methods for interpreting and visualizing neural models have also been significantly explored in vision (Vondrick et al., 2013; Vedaldi et al., 2014; Zeiler and Fergus, 2014; Weinzaepfel et al., 2011; Erhan et al., 2009; Simonyan et al., 2013; Klöppel et al., 2008), which we do not describe here for ”
Audio Visual Attribute Discovery for Fine-Grained Object Recognition (2018, methodology): “Belhumeur 2013; Elhoseiny, Saleh, and Elgammal 2013; Reed et al. 2016; Vedaldi et al. 2014; Zhang et al. 2013; He and Peng 2017).”
Weakly Supervised Fine-Grained Image Categorization (2015, background): “…traditional image recognition such as scene or object recognition, ﬁne-grained categorization deals with images with subtle distinctions, which usually involves the classiﬁcation of subclasses of objects belonging to the same class like birds [26, 1], dogs [16], planes [25], plants [19, 23], etc.”
I Have Seen Enough: Transferring Parts Across Categories (2016, background): “Unfortunately, datasets that have keypoints or part-level annotations either consider a handful of classes, such as the PASCAL Parts [4], or are specialized to a narrow set of domains, focusing only on birds [57], faces [32, 63], or planes [55].”
Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network (2015, background): “Research on attribute-based visual representations have received renewed attention by the computer vision community in the past few years [27, 11, 34, 43].”
Part-Stacked CNN for Fine-Grained Visual Categorization (2015, methodology): “Based on manually-labeled strong part annotations, the proposed architecture consists of a fully convolutional network to locate multiple object parts and a two-stream classification network that encodes object-level and part-level cues simultaneously.”
Deep domain adaptation for describing people based on fine-grained clothing attributes (2015, background): “There are only a few attribute datasets with fine-grained annotations, for example, datasets related to detailed descriptions of birds [43] and aircrafts [42].”
Learning to lip read words by watching videos (2018, methodology): “Our implementation is based on the MATLAB toolbox MatConvNet [43] and Caffe [44].”
Learning Attributes Equals Multi-Source Domain Generalization (2016, background): “Indeed, most of the existing attribute detectors [44, 18, 42, 9, 32, 35, 8, 10, 12, 75, 31] are built using features engineered or learned for object recognition together with off-shelf machine learning classiﬁers— without tailoring them to reﬂect the idiosyncrasies of attributes.”