Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection

Author(s):  
Grant Van Horn ◽  
Steve Branson ◽  
Ryan Farrell ◽  
Scott Haber ◽  
Jessie Barry ◽  
...  
Author(s):  
Anil S. Baslamisli ◽  
Partha Das ◽  
Hoang-An Le ◽  
Sezer Karaoglu ◽  
Theo Gevers

AbstractIn general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.


2021 ◽  
Vol 9 ◽  
pp. 995-1011
Author(s):  
Takuma Udagawa ◽  
Akiko Aizawa

Abstract Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication. While various task settings have been proposed in existing literature, they mostly focus on creating common ground under a static context and ignore the aspect of maintaining them overtime under dynamic context. In this work, we propose a novel task setting to study the ability of both creating and maintaining common ground in dynamic environments. Based on our minimal task formulation, we collected a large-scale dataset of 5,617 dialogues to enable fine-grained evaluation and analysis of various dialogue systems. Through our dataset analyses, we highlight novel challenges introduced in our setting, such as the usage of complex spatio-temporal expressions to create and maintain common ground. Finally, we conduct extensive experiments to assess the capabilities of our baseline dialogue system and discuss future prospects of our research.


2019 ◽  
Vol 22 (3) ◽  
pp. 365-380 ◽  
Author(s):  
Matthias Olthaar ◽  
Wilfred Dolfsma ◽  
Clemens Lutz ◽  
Florian Noseleit

In a competitive business environment at the Bottom of the Pyramid smallholders supplying global value chains may be thought to be at the whims of downstream large-scale players and local market forces, leaving no room for strategic entrepreneurial behavior. In such a context we test the relationship between the use of strategic resources and firm performance. We adopt the Resource Based Theory and show that seemingly homogenous smallholders deploy resources differently and, consequently, some do outperform others. We argue that the ‘resource-based theory’ results in a more fine-grained understanding of smallholder performance than approaches generally applied in agricultural economics. We develop a mixed-method approach that allows one to pinpoint relevant, industry-specific resources, and allows for empirical identification of the relative contribution of each resource to competitive advantage. The results show that proper use of quality labor, storage facilities, time of selling, and availability of animals are key capabilities.


Author(s):  
Jin Zhou ◽  
Qing Zhang ◽  
Jian-Hao Fan ◽  
Wei Sun ◽  
Wei-Shi Zheng

AbstractRecent image aesthetic assessment methods have achieved remarkable progress due to the emergence of deep convolutional neural networks (CNNs). However, these methods focus primarily on predicting generally perceived preference of an image, making them usually have limited practicability, since each user may have completely different preferences for the same image. To address this problem, this paper presents a novel approach for predicting personalized image aesthetics that fit an individual user’s personal taste. We achieve this in a coarse to fine manner, by joint regression and learning from pairwise rankings. Specifically, we first collect a small subset of personal images from a user and invite him/her to rank the preference of some randomly sampled image pairs. We then search for the K-nearest neighbors of the personal images within a large-scale dataset labeled with average human aesthetic scores, and use these images as well as the associated scores to train a generic aesthetic assessment model by CNN-based regression. Next, we fine-tune the generic model to accommodate the personal preference by training over the rankings with a pairwise hinge loss. Experiments demonstrate that our method can effectively learn personalized image aesthetic preferences, clearly outperforming state-of-the-art methods. Moreover, we show that the learned personalized image aesthetic benefits a wide variety of applications.


Geosciences ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 41
Author(s):  
Tim Jurisch ◽  
Stefan Cantré ◽  
Fokke Saathoff

A variety of studies recently proved the applicability of different dried, fine-grained dredged materials as replacement material for erosion-resistant sea dike covers. In Rostock, Germany, a large-scale field experiment was conducted, in which different dredged materials were tested with regard to installation technology, stability, turf development, infiltration, and erosion resistance. The infiltration experiments to study the development of a seepage line in the dike body showed unexpected measurement results. Due to the high complexity of the problem, standard geo-hydraulic models proved to be unable to analyze these results. Therefore, different methods of inverse infiltration modeling were applied, such as the parameter estimation tool (PEST) and the AMALGAM algorithm. In the paper, the two approaches are compared and discussed. A sensitivity analysis proved the presumption of a non-linear model behavior for the infiltration problem and the Eigenvalue ratio indicates that the dike infiltration is an ill-posed problem. Although this complicates the inverse modeling (e.g., termination in local minima), parameter sets close to an optimum were found with both the PEST and the AMALGAM algorithms. Together with the field measurement data, this information supports the rating of the effective material properties of the applied dredged materials used as dike cover material.


2021 ◽  
Vol 7 (3) ◽  
pp. 50
Author(s):  
Anselmo Ferreira ◽  
Ehsan Nowroozi ◽  
Mauro Barni

The possibility of carrying out a meaningful forensic analysis on printed and scanned images plays a major role in many applications. First of all, printed documents are often associated with criminal activities, such as terrorist plans, child pornography, and even fake packages. Additionally, printing and scanning can be used to hide the traces of image manipulation or the synthetic nature of images, since the artifacts commonly found in manipulated and synthetic images are gone after the images are printed and scanned. A problem hindering research in this area is the lack of large scale reference datasets to be used for algorithm development and benchmarking. Motivated by this issue, we present a new dataset composed of a large number of synthetic and natural printed face images. To highlight the difficulties associated with the analysis of the images of the dataset, we carried out an extensive set of experiments comparing several printer attribution methods. We also verified that state-of-the-art methods to distinguish natural and synthetic face images fail when applied to print and scanned images. We envision that the availability of the new dataset and the preliminary experiments we carried out will motivate and facilitate further research in this area.


2021 ◽  
Vol 13 (5) ◽  
pp. 905
Author(s):  
Chuyi Wu ◽  
Feng Zhang ◽  
Junshi Xia ◽  
Yichen Xu ◽  
Guoqing Li ◽  
...  

The building damage status is vital to plan rescue and reconstruction after a disaster and is also hard to detect and judge its level. Most existing studies focus on binary classification, and the attention of the model is distracted. In this study, we proposed a Siamese neural network that can localize and classify damaged buildings at one time. The main parts of this network are a variety of attention U-Nets using different backbones. The attention mechanism enables the network to pay more attention to the effective features and channels, so as to reduce the impact of useless features. We train them using the xBD dataset, which is a large-scale dataset for the advancement of building damage assessment, and compare their result balanced F (F1) scores. The score demonstrates that the performance of SEresNeXt with an attention mechanism gives the best performance, with the F1 score reaching 0.787. To improve the accuracy, we fused the results and got the best overall F1 score of 0.792. To verify the transferability and robustness of the model, we selected the dataset on the Maxar Open Data Program of two recent disasters to investigate the performance. By visual comparison, the results show that our model is robust and transferable.


Sign in / Sign up

Export Citation Format

Share Document