Fast, Accurate Detection of 100,000 Object Classes on a Single Machine

By Thomas L. Dean, Mark A. Ruzon, Mark E. Segal, Jonathon Shlens, Sudheendra Vijayanarasimhan, Jay Yagnik. 2013

363 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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 Evaluation & Benchmarks

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “Best paper awards at top vision conferences in 2013 were awarded to large-scale recognition methods: at CVPR 2013 to ”Fast, Accurate Detection of 100,000 Object Classes on a Single Machine” (Dean et al., 2013) and at ICCV 2013 to ”From Large Scale Image Cate-gorization to Entry-Level Categories” (Or”
Quantization based Fast Inner Product Search (2015, background): “Similarly, a large scale classification system needs to classify an item into one of the categories, where the number of categories may be very large [9].”
Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS) (2014, background): “Classifying with large number of possible class labels is common in multi-label learning and fine grained object classification, for instance, prediction task with ∣L∣ = 100,000 [7].”
You Only Look Once: Unified, Real-Time Object Detection (2015, background): “[5] [37] [30] [14] [17] [27] However, only Sadeghi et al.”
Scalable Object Detection Using Deep Neural Networks (2013, methodology): “A hashing based approach for efficient part detection has shown good results as well [3].”
Towards Open Set Deep Networks (2015, background): “Co-evolution of rich representations, scalable classification methods and large datasets have resulted in many commercial applications [5, 28, 16, 6].”
Towards Open World Recognition (2014, background): “Co-evolution of rich classification models along with advances in datasets have resulted in many commercial applications [8, 40, 29].”
Automatically Discovering and Learning New Visual Categories with Ranking Statistics (2020, background): “Finally, other works (Dean et al., 2013; Yagnik et al., 2011) discuss the application of rank statistics to measuring the similarity of vectors; however, to the best of our knowledge, we are the ﬁrst to apply rank statistics to the task of novel category discovery using deep neural networks.”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, background): “Fast object detection algorithms often gain high interests [4], [12], [19], [40], [90].”
Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization (2014, methodology): “Recent years have witnessed the great success of hashing techniques for scalable similarity search in many real applications (Torralba, Fergus, and Weiss 2008; Salakhutdinov and Hinton 2009; Kong and Li 2012a; He et al. 2012; Tseng et al. 2012; Dean et al. 2013; Wang et al. 2013; Xu et al. 2013; Zha”
Hard negative classes for multiple object detection (2014, methodology): “We use one of the two clusters and a cluster of negative samples created by randomly choosing windows from negative images, to train the SVM and obtain a model consisting of M components.”
Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models (2014, methodology): “For instance, the recent part-based hashing technique of [10] could be directly applied to our algorithm by applying winner-take-all hashing [40] on the discriminative visual elements.”
Best of both worlds: Human-machine collaboration for object annotation (2015, background): “The field of large-scale object detection has leaped forward in the past few years [20, 43, 11, 45, 61, 24, 53], with significant progress both in techniques [20, 43, 53, 45] as well as scale: hundreds of thousands of object detectors can now be trained directly from web data [8, 15, 11].”
Training Deformable Part Models with Decorrelated Features (2013, methodology): “In contemporaneous work, a hashing technique promises fast detection with 100,000 DPMs on a single workstation [6].”
CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise (2017, neutral): “For classification tasks with millions of classes [4, 8], it is infeasible to have even one manual annotation per class.”
Learning descriptors for object recognition and 3D pose estimation (2015, methodology): “Our approach is clearly in the framework of 2D view specific templates [15], which is conceptually sim ple, supported by psychophysical experiments [33], and was successfully applied to various problems and datasets over the last years [22, 19, 13, 11, 8, 28].”
Salient object detection: A survey (2014, background): “, from typically a few millions to less than a few thousands), especially when the number of object classes that need to be detected is high [71], and 3) also improves the detection accuracy by allowing the”
On Symmetric and Asymmetric LSHs for Inner Product Search (2014, methodology): “…when using matrix-factorization based recommendation systems (Koren et al., 2009; Srebro et al., 2005; Cremonesi et al., 2010), in multi-class prediction (Dean et al., 2013; Jain et al., 2009) and structural SVM (Joachims, 2006; Joachims et al., 2009) problems and in vision problems when scoring…”