SqueezeGAN: Image to Image Translation With Minimum Parameters

Kelkar, Sachin; Rastogi, Chetanya; Gupta, Sparsh; Pillai, G. N.

doi:10.1109/ijcnn.2018.8489587

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This representation allows us to use extensive literature on image-to-image translation that has been very well studied in the computer vision community [28,38,52,72,76]. These algorithms have utilized generator models paired with appropriate targets and loss functions to solve many image-to-image translation problems like image denoising [10,71], image superresolution [15,28,32], image colorization [27,31], and real-to-art image translations [26,27,76]. While there has been some work that utilizes rf-based techniques that utilize machine learning to solve through-wall human pose estimation [58,73,74], our paper is the first to present general principles for using ideas of imageto-image translation for the localization problem.…”

Section: Related Workmentioning

confidence: 99%

Deep learning based wireless localization for indoor navigation

Ayyalasomayajula

Arun

et al. 2020

Proceedings of the 26th Annual International Conference on Mobile Computing and Networking

138

View full text Add to dashboard Cite

Location services, fundamentally, rely on two components: a mapping system and a positioning system. The mapping system provides the physical map of the space, and the positioning system identifies the position within the map. Outdoor location services have thrived over the last couple of decades because of well-established platforms for both these components (e.g. Google Maps for mapping, and GPS for positioning). In contrast, indoor location services haven't caught up because of the lack of reliable mapping and positioning frameworks. Wi-Fi positioning lacks maps and is also prone to environmental errors. In this paper, we present DLoc, a Deep Learning based wireless localization algorithm that can overcome traditional limitations of RF-based localization approaches (like multipath, occlusions, etc.). We augment DLoc with an automated mapping platform, MapFind. MapFind constructs location-tagged maps of the environment and generates training data for DLoc. Together, they allow off-the-shelf Wi-Fi devices like smartphones to access a map of the environment and to estimate their position with respect to that map. During our evaluation, MapFind has collected location estimates of over 105 thousand points under 8 different scenarios with varying furniture positions and people motion across two different spaces covering 2000 sq. Ft. DLoc outperforms stateof-the-art methods in Wi-Fi-based localization by 80% (median & 90 th percentile) across the two different spaces. CCS CONCEPTS • Networks → Location based services; • Computing methodologies → Robotic planning; Supervised learning; • Information systems → Sensor networks.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep learning based wireless localization for indoor navigation

Ayyalasomayajula

Arun

et al. 2020

Proceedings of the 26th Annual International Conference on Mobile Computing and Networking

138

View full text Add to dashboard Cite

show abstract

“…Adversarial training and Generative Adversarial Networks (GANs) (Goodfellow et al, 2014) have been successfully applied to Computer Vision (Karras et al, 2017;Kelkar et al, 2018) and Natural Language Processing (Lin et al, 2017) applications, but only sparsely studied in Information Retrieval tasks. As described by , adversarial training in Information Retrieval can be approached by having a generator model to sample difficult adversarial examples which are passed to a discriminator model that learns to rank on increasingly difficult adversarial examples.…”

Section: Introductionmentioning

confidence: 99%

“…Adversarial training and Generative Adversarial Networks (GANs) (Goodfellow et al, 2014) have been successfully applied to Computer Vision (Karras et al, 2017;Kelkar et al, 2018) and Natural Language Processing (Lin et al, 2017) applications, but only sparsely studied in Information Retrieval tasks. As described by To help address this issue, we propose a novel committee representation to adversarial modeling for QA ranking that can be applied to any underlying ranking algorithm.…”

Section: Introductionmentioning

confidence: 99%

On Committee Representations of Adversarial Learning Models for Question-Answer Ranking

Gupta

Carvalho

2019

Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)

Self Cite

View full text Add to dashboard Cite

Adversarial training is a process in Machine Learning that explicitly trains models on adversarial inputs (inputs designed to deceive or trick the learning process) in order to make it more robust or accurate. In this paper we investigate how representing adversarial training models as committees can be used to effectively improve the performance of Question-Answer (QA) Ranking. We start by empirically probing the effects of adversarial training over multiple QA ranking algorithms, including the state-of-the-art Multihop Attention Network model. We evaluate these algorithms on several benchmark datasets and observe that, while adversarial training is beneficial to most baseline algorithms, there are cases where it may lead to overfitting and performance degradation. We investigate the causes of such degradation, and then propose a new representation procedure for this adversarial learning problem, based on committee learning, that not only is capable of consistently improving all baseline algorithms, but also outperforms the previous state-of-the-art algorithm by as much as 6% in NDCG (Normalized Discounted Cumulative Gain).

show abstract

SqueezeGAN: Image to Image Translation With Minimum Parameters

Cited by 2 publications

References 15 publications

Deep learning based wireless localization for indoor navigation

Deep learning based wireless localization for indoor navigation

On Committee Representations of Adversarial Learning Models for Question-Answer Ranking

Contact Info

Product

Resources

About