Feature encoding in band-limited distributed surveillance systems

Rahimpour, Alireza; Taalimi, Ali; Qi, Hairong

doi:10.1109/icassp.2017.7952457

Cited by 11 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It includes various popular matrix norms as special cases such as the Frobenius norm (p = q = 2), the max norm (p = q = ∞), and the 1-norm (p = 1, q = ∞). This class has had numerous applications in machine learning, statistics, and signal processing (Kowalski, 2009;Ding et al, 2006;Kong et al, 2011;Nie et al, 2010;Zhaoshui and Cichocki, 2008;Rahimpour et al, 2017;Kashlak and Kong, 2021;Cai et al, 2011). Moreover, unlike some other matrix norm classes (like Schatten or induced norm classes) the entrywise L(p, q) class is quite interpretable; for instance, the L(1, 1) loss simply sums up the absolute differences between the overall scores given by reviewers and those given by the function f .…”

Section: Loss Functionsmentioning

confidence: 99%

Loss Functions, Axioms, and Peer Review

Noothigattu¹,

Shah²,

Procaccia³

2021

jair

View full text Add to dashboard Cite

It is common to see a handful of reviewers reject a highly novel paper, because they view, say, extensive experiments as far more important than novelty, whereas the community as a whole would have embraced the paper. More generally, the disparate mapping of criteria scores to final recommendations by different reviewers is a major source of inconsistency in peer review. In this paper we present a framework inspired by empirical risk minimization (ERM) for learning the community's aggregate mapping. The key challenge that arises is the specification of a loss function for ERM. We consider the class of L(p,q) loss functions, which is a matrix-extension of the standard class of Lp losses on vectors; here the choice of the loss function amounts to choosing the hyperparameters p and q. To deal with the absence of ground truth in our problem, we instead draw on computational social choice to identify desirable values of the hyperparameters p and q. Specifically, we characterize p=q=1 as the only choice of these hyperparameters that satisfies three natural axiomatic properties. Finally, we implement and apply our approach to reviews from IJCAI 2017.

show abstract

Section: Loss Functionsmentioning

confidence: 99%

Loss Functions, Axioms, and Peer Review

Noothigattu¹,

Shah²,

Procaccia³

2021

jair

View full text Add to dashboard Cite

show abstract

“…We consider an "entrywise norm" of the type l p,q for some p, q ≥ 1 defined for a matrix X as (see [37]):…”

Section: Norms and Errorsmentioning

confidence: 99%

Error Control and Loss Functions for the Deep Learning Inversion of Borehole Resistivity Measurements

Shahriari¹,

Pardo²,

Rivera³

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep learning (DL) is a numerical method that approximates functions. Recently, its use has become attractive for the simulation and inversion of multiple problems in computational mechanics, including the inversion of borehole logging measurements for oil and gas applications. In this context, DL methods exhibit two key attractive features: a) once trained, they enable to solve an inverse problem in a fraction of a second, which is convenient for borehole geosteering operations as well as in other real-time inversion applications. b) DL methods exhibit a superior capability for approximating highly-complex functions across different areas of knowledge. Nevertheless, as it occurs with most numerical methods, DL also relies on expert design decisions that are problem specific to achieve reliable and robust results. Herein, we investigate two key aspects of deep neural networks (DNNs) when applied to the inversion of borehole resistivity measurements: error control and adequate selection of the loss function. As we illustrate via theoretical considerations and extensive numerical experiments, these interrelated aspects are critical to recover accurate inversion results.

show abstract

“…Representation learning is key to computer vision tasks. Recently with the explosion of data availability, it is crucial for the representation to be computationally efficient as well [1,2,3]. Consequently learning high-quality binary representation is tempting due to its compactness and representation capacity.…”

Section: Introductionmentioning

confidence: 99%

End-to-end binary representation learning via direct binary embedding

Liu

Rahimpour

Taalimi

et al. 2017

2017 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Learning binary representation is essential to large-scale computer vision tasks. Most existing algorithms require a separate quantization constraint to learn effective hashing functions. In this work, we present Direct Binary Embedding (DBE), a simple yet very effective algorithm to learn binary representation in an end-to-end fashion. By appending an ingeniously designed DBE layer to the deep convolutional neural network (DCNN), DBE learns binary code directly from the continuous DBE layer activation without quantization error. By employing the deep residual network (ResNet) as DCNN component, DBE captures rich semantics from images. Furthermore, in the effort of handling multilabel images, we design a joint cross entropy loss that includes both softmax cross entropy and weighted binary cross entropy in consideration of the correlation and independence of labels, respectively. Extensive experiments demonstrate the significant superiority of DBE over state-of-the-art methods on tasks of natural object recognition, image retrieval and image annotation.

show abstract

Feature encoding in band-limited distributed surveillance systems

Cited by 11 publications

References 27 publications

Loss Functions, Axioms, and Peer Review

Loss Functions, Axioms, and Peer Review

Error Control and Loss Functions for the Deep Learning Inversion of Borehole Resistivity Measurements

End-to-end binary representation learning via direct binary embedding

Contact Info

Product

Resources

About