Discriminatively Activated Sparselets

By Ross B. Girshick, Hyun Oh Song, Trevor Darrell. 2013

33 citations recorded by the source corpus.

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

Speeding up Convolutional Neural Networks with Low Rank Expansions (2014, methodology): “One way to exploit this redundancy is to approximate the filter set by a linear combination of a smaller basis set of M filters [32, 35, 36].”
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, background): “neural network and autoencoder for training more effective sparselets [90] to achieve efficient scene classification and object detection.”
FPM: Fine Pose Parts-Based Model with 3D CAD Models (2014, background): “weights of the root and part models as described in [14] allowing us to search this rather large space of fine poses in a reasonable amount of time.”
Feature representation for statistical-learning-based object detection: A review (2015, methodology): “Discriminatively activated sparselets [27] further partition wi into several blocks and use a structural SVM to learn the activation coefficients.”
Learning coarse-to-fine sparselets for efficient object detection and scene classification (2015, methodology): “However, as pointed out by [2] and [3], the method proposed by Song et al.”
The Fastest Deformable Part Model for Object Detection (2014, background): “Acceleration of Multi-category DPM Quite a large number of recent works [23, 27, 15, 3, 17] were proposed to accelerate DPM for multi-category detection, e.g. simultaneous detection of 20 categories on Pascal VOC.”
Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification (2015, methodology): “ges, where patches from the same class can be very dierent, while patches from dierent classes can be highly similar, thus, max-margin based discriminative learning cannot be directly used here. In [43, 44], object part lters at the middle level are shared to represent a large number of object categ”
Learning Everything about Anything: Webly-Supervised Visual Concept Learning (2014, methodology): “This testing step can be easily sped up by leveraging recent fast detection methods [10, 14, 46].”