Detecting Arbitrary Oriented Text in the Wild with a Visual Attention Model

Huang, Wenyi; He, Dafang; Yang, Xin; Zhou, Zihan; Kifer, Daniel; Giles, C. Lee

doi:10.1145/2964284.2967282

Cited by 13 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As with other DL models, however, this work does not assume the forcings or the target observations to be perfect. The Artificial Intelligence community has worked extensively with data “in the wild,” that is, large but low‐quality data sets, and DL models appear to deliver good performance even if there is significant noise (Huang et al., 2016; Izadinia et al., 2015; Stadelmann et al., 2018). What will mislead models are systematic errors, which is what this methodology proposes to improve.…”

Section: Resultsmentioning

confidence: 99%

Evaluating the Potential and Challenges of an Uncertainty Quantification Method for Long Short‐Term Memory Models for Soil Moisture Predictions

Fang

Kifer

Lawson

2020

Water Resources Research

Self Cite

View full text Add to dashboard Cite

Recently, recurrent deep networks have shown promise to harness newly available satellite-sensed data for long-term soil moisture projections. However, to be useful in forecasting, deep networks must also provide uncertainty estimates. Here we evaluated Monte Carlo dropout with an input-dependent data noise term (MCD+N), an efficient uncertainty estimation framework originally developed in computer vision, for hydrologic time series predictions. MCD+N simultaneously estimates a heteroscedastic input-dependent data noise term (a trained error model attributable to observational noise) and a network weight uncertainty term (attributable to insufficiently constrained model parameters). Although MCD+N has appealing features, many heuristic approximations were employed during its derivation, and rigorous evaluations and evidence of its asserted capability to detect dissimilarity were lacking. To address this, we provided an in-depth evaluation of the scheme's potential and limitations. We showed that for reproducing soil moisture dynamics recorded by the Soil Moisture Active Passive (SMAP) mission, MCD+N indeed gave a good estimate of predictive error, provided that we tuned a hyperparameter and used a representative training data set. The input-dependent term responded strongly to observational noise, while the model term clearly acted as a detector for physiographic dissimilarity from the training data, behaving as intended. However, when the training and test data were characteristically different, the input-dependent term could be misled, undermining its reliability. Additionally, due to the data-driven nature of the model, data noise also influences network weight uncertainty, and therefore the two uncertainty terms are correlated. Overall, this approach has promise, but care is needed to interpret the results.

show abstract

Section: Resultsmentioning

confidence: 99%

Evaluating the Potential and Challenges of an Uncertainty Quantification Method for Long Short‐Term Memory Models for Soil Moisture Predictions

Fang

Kifer

Lawson

2020

Water Resources Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Huang et al [26] utilized the recurrent attention model to detect arbitrary oriented text in the wild and achieved state-of-the-art accuracy on ICDAR 2013 and MSRA-TD500. However, their detection pipeline depends on extremal regions to generate initial attention proposals and on CNN classifiers to filter non-text proposals.…”

Section: Visual Attention Modelmentioning

confidence: 99%

Traffic signal detection and classification in street views using an attention model

Zhang

et al. 2018

Comp. Visual Media

View full text Add to dashboard Cite

Detecting small objects is a challenging task. We focus on a special case: the detection and classification of traffic signals in street views. We present a novel framework that utilizes a visual attention model to make detection more efficient, without loss of accuracy, and which generalizes. The attention model is designed to generate a small set of candidate regions at a suitable scale so that small targets can be better located and classified. In order to evaluate our method in the context of traffic signal detection, we have built a traffic light benchmark with over 15,000 traffic light instances, based on Tencent street view panoramas. We have tested our method both on the dataset we have built and the Tsinghua-Tencent 100K (TT100K) traffic sign benchmark. Experiments show that our method has superior detection performance and is quicker than the general faster RCNN object detection framework on both datasets. It is competitive with state-of-theart specialist traffic sign detectors on TT100K, but is an order of magnitude faster. To show generality, we tested it on the LISA dataset without tuning, and obtained an average precision in excess of 90%.

show abstract

“…Volunteer scientists can also be requested for results in an active learning framework (Settles, 2012), i.e., 10 they can be queried for more data for instances that can best reduce the uncertainty of the predictions. Crowd-sourced data have played roles in deep learning research (Huang et al, 2016;Izadinia et al, 2015), even though there are problems related to data quality. An important co-benefits of involving citizen scientists is the education and outreach to the public.…”

Section: Collecting Big Data Through Data Sharing and Citizen Scientistsmentioning

confidence: 99%

HESS Opinions: Deep learning as a promising avenue toward knowledge discovery in water sciences

Laloy

Albert

Chang

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming industry applications and generating new and improved capabilities for scientific discovery and model building. The adoption of DL in water science 20 has so far been gradual, but the related fields are now ripe for breakthroughs. This paper proposes that DL-based methods can open up a viable, complementary avenue toward knowledge discovery in hydrologic sciences. In the new avenue, machinelearning algorithms present competing hypotheses that are consistent with data for scientists to further evaluate. Interrogative studies are invoked to interpret DL models. In addition, we lay out several opinions shared by authors: (1) deep learning may bring forth transformative progress to the field of hydrology due to its ability to assimilate big data and identify commonalities 25 and differences; (2) the community may benefit greatly from a variety of shared datasets and open competitions; (3) big hydrologic data can be obtained via various ways including data compilation and working with citizen scientists, which offers the co-benefits of education and stakeholder engagement; (4) water sciences, and hydrology in particular, offer a unique set of challenges that can, in turn, stimulate advances in machine learning; and (5) An urgent need for research is hydrologycustomized methods for interpreting knowledge extracted by deep learning. 30Hydrol. Earth Syst. Sci. Discuss., https://doi.

show abstract

Detecting Arbitrary Oriented Text in the Wild with a Visual Attention Model

Cited by 13 publications

References 25 publications

Evaluating the Potential and Challenges of an Uncertainty Quantification Method for Long Short‐Term Memory Models for Soil Moisture Predictions

Evaluating the Potential and Challenges of an Uncertainty Quantification Method for Long Short‐Term Memory Models for Soil Moisture Predictions

Traffic signal detection and classification in street views using an attention model

HESS Opinions: Deep learning as a promising avenue toward knowledge discovery in water sciences

Contact Info

Product

Resources

About