Learning Detectors Quickly with Stationary Statistics

Valmadre, Jack; Sridharan, Sridha; Lucey, Simon

doi:10.1007/978-3-319-16865-4_7

Cited by 4 publications

(3 citation statements)

References 40 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We found that it was important to provide the Correlation Filter with a large region of context in the training image, which is consistent with the findings of Danelljan et al [8] and Kiani et al [16]. To reduce the effect of circular boundaries, the feature map x is pre-multiplied by a cosine window [4] and the final template is cropped [30].…”

Section: Correlation Filter Networksupporting

confidence: 86%

End-to-End Representation Learning for Correlation Filter Based Tracking

Valmadre

Bertinetto

Henriques

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

1,447

1,136

View full text Add to dashboard Cite

Training image: 255x255x3 Test image: 255x255x3 17x17x32 49x49x32 Correlation Filter Crop ★ 33x33x1 CNN CNN 49x49x32 Figure 1: Overview of the proposed network architecture, CFNet. It is an asymmetric Siamese network: after applying the same convolutional feature transform to both input images, the "training image" is used to learn a linear template, which is then applied to search the "test image" by cross-correlation. AbstractThe Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution, enabling the detector to be re-trained once per frame. Previous works that use the Correlation Filter, however, have adopted features that were either manually designed or trained for a different task. This work is the first to overcome this limitation by interpreting the Correlation Filter learner, which has a closed-form solution, as a differentiable layer in a deep neural network. This enables learning deep features that are tightly coupled to the Correlation Filter. Experiments illustrate that our method has the important practical benefit of allowing lightweight architectures to achieve state-of-the-art performance at high framerates. * Equal first authorship. is challenging. This problem emerges naturally in applications such as visual object tracking, where the goal is to re-detect an object over a video with the sole supervision of a bounding box at the beginning of the sequence. The main challenge is the lack of a-priori knowledge of the target object, which can be of any class.The simplest approach is to disregard the lack of a-priori knowledge and adapt a pre-trained deep convolutional neural network (CNN) to the target, for example by using stochastic gradient descent (SGD), the workhorse of deep network optimization [32,26,36]. The extremely limited training data and large number of parameters make this a difficult learning problem. Furthermore, SGD is quite expensive for online adaptation [32,26].

show abstract

Section: Correlation Filter Networksupporting

confidence: 86%

End-to-End Representation Learning for Correlation Filter Based Tracking

Valmadre

Bertinetto

Henriques

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

1,447

1,136

View full text Add to dashboard Cite

show abstract

“…This implies that each component is a member of a set of structured matrices, M l . This structure could be, but not limited to, block sparse [8], diagonal, Toeplitz or circulant [13], [26] as these structures provide redundancies which enable multiplication to be performed efficiently.…”

Section: A Objective and Structurementioning

confidence: 99%

Fast, Dense Feature SDM on an iPhone

Fagg

Lucey

Sridharan

2017

2017 12th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2017)

Self Cite

View full text Add to dashboard Cite

In this paper, we present our method for enabling dense SDM to run at over 90 FPS on a mobile device. Our contributions are two-fold. Drawing inspiration from the FFT, we propose a Sparse Compositional Regression (SCR) framework, which enables a significant speed up over classical dense regressors. Second, we propose a binary approximation to SIFT features. Binary Approximated SIFT (BASIFT) features, which are a computationally efficient approximation to SIFT, a commonly used feature with SDM. We demonstrate the performance of our algorithm on an iPhone 7, and show that we achieve similar accuracy to SDM.

show abstract

“…We leverage recent work on rapid estimation of LDA classifiers [3,19] to achieve this goal, though fast correlation filter estimation [4] is potentially equally applicable. The method we present is largely agnostic to the objective used to learn the linear detectors (e.g.…”

Section: Prior Artmentioning

confidence: 99%

Dense Semantic Correspondence Where Every Pixel is a Classifier

Bristow

Valmadre

Lucey

2015

2015 IEEE International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

Determining dense semantic correspondences across objects and scenes is a difficult problem that underpins many higher-level computer vision algorithms. Unlike canonical dense correspondence problems which consider images that are spatially or temporally adjacent, semantic correspondence is characterized by images that share similar high-level structures whose exact appearance and geometry may differ.Motivated by object recognition literature and recent work on rapidly estimating linear classifiers, we treat semantic correspondence as a constrained detection problem, where an exemplar LDA classifier is learned for each pixel. LDA classifiers have two distinct benefits: (i) they exhibit higher average precision than similarity metrics typically used in correspondence problems, and (ii) unlike exemplar SVM, can output globally interpretable posterior probabilities without calibration, whilst also being significantly faster to train.We pose the correspondence problem as a graphical model, where the unary potentials are computed via convolution with the set of exemplar classifiers, and the joint potentials enforce smoothly varying correspondence assignment.

show abstract

Learning Detectors Quickly with Stationary Statistics

Cited by 4 publications

References 40 publications

End-to-End Representation Learning for Correlation Filter Based Tracking

End-to-End Representation Learning for Correlation Filter Based Tracking

Fast, Dense Feature SDM on an iPhone

Dense Semantic Correspondence Where Every Pixel is a Classifier

Contact Info

Product

Resources

About