Title: CNN-Based Non-contact Detection of Food Level in Bottles from RGB Images
In this paper, we present an approach that detects the level of food in store-bought containers using deep convolutional neural networks (CNNs) trained on RGB images captured using an off-the-shelf camera. Our approach addresses three challenges—the diversity in container geometry, the large variations in shapes and appearances of labels on store-bought containers, and the variability in color of container contents—by augmenting the data used to train the CNNs using printed labels with synthetic textures attached to the training bottles, interchanging the contents of the bottles of the training containers, and randomly altering the intensities of blocks of pixels in the labels and at the bottle borders. Our approach provides an average level detection accuracy of 92.4% using leave-one-out cross-validation on 10 store-bought bottles of varying geometries, label appearances, label shapes, and content colors.
Zhu, Zhaowei; Song, Yiwen; Liu, Yang(
, roceedings of the 38th International Conference on Machine Learning)
Meila, Marina; Zhang, Tong
(Ed.)
The label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy labels. Existing works heavily rely on finding “anchor points” or their approximates, defined as instances belonging to a particular class almost surely. Nonetheless, finding anchor points remains a non-trivial task, and the estimation accuracy is also often throttled by the number of available anchor points. In this paper, we propose an alternative option to the above task. Our main contribution is the discovery of an efficient estimation procedure based on a clusterability condition. We provemore »that with clusterable representations of features, using up to third-order consensuses of noisy labels among neighbor representations is sufficient to estimate a unique transition matrix. Compared with methods using anchor points, our approach uses substantially more instances and benefits from a much better sample complexity. We demonstrate the estimation accuracy and advantages of our estimates using both synthetic noisy labels (on CIFAR-10/100) and real human-level noisy labels (on Clothing1M and our self-collected human-annotated CIFAR-10). Our code and human-level noisy CIFAR-10 labels are available at https://github.com/UCSC-REAL/HOC.« less
Walmsley, Mike; Smith, Lewis; Lintott, Chris; Gal, Yarin; Bamford, Steven; Dickinson, Hugh; Fortson, Lucy; Kruk, Sandor; Masters, Karen; Scarlata, Claudia; et al(
, Monthly Notices of the Royal Astronomical Society)
ABSTRACT
We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN can learn from galaxy images with uncertain labels and then, for previously unlabelled galaxies, predict the probability of each possible label. Our posteriors are well-calibrated (e.g. for predicting bars, we achieve coverage errors of 11.8 per cent within a vote fraction deviation of 0.2) and hence are reliable for practical use. Further, using our posteriors, we apply the active learning strategy BALD to request volunteer responses for the subset of galaxies which, if labelled,more »would be most informative for training our network. We show that training our Bayesian CNNs using active learning requires up to 35–60 per cent fewer labelled galaxies, depending on the morphological feature being classified. By combining human and machine intelligence, Galaxy zoo will be able to classify surveys of any conceivable scale on a time-scale of weeks, providing massive and detailed morphology catalogues to support research into galaxy evolution.
Hossain, S; Roy, N.(
, Proceedings of the IEEE AAAI 2018 Fall Symposium, Oct 2018)
Precise and eloquent label information is fundamental for interpreting the underlying data distributions distinctively and training of supervised and semi-supervised learning models adequately. But obtaining large amount of labeled data demands substantial manual effort. This obligation can be mitigated by acquiring labels of most informative data instances using Active Learning. However labels received from humans are not always reliable and poses the risk of introducing noisy class labels which will degrade the efficacy of a model instead of its improvement. In this paper, we address the problem of annotating sensor data instances of various Activities of Daily Living (ADLs) inmore »smart home context. We exploit the interactions between the users and annotators in terms of relationships spanning across spatial and temporal space which accounts for an activity as well. We propose a novel annotator selection model SocialAnnotator which exploits the interactions between the users and annotators and rank the annotators based on their level of correspondence. We also introduce a novel approach to measure this correspondence distance using the spatial and temporal information of interactions, type of the relationships and activities. We validate our proposed SocialAnnotator framework in smart environments achieving ≈ 84% statistical confidence in data annotation« less
Zhan, Yang; Conway, Alex; Jiao, Yizheng; Mukherjee, Nirjhar; Groombridge, Ian; Bender, Michael A.; Farach-Colton, Martin; Jannen, William; Johnson, Rob; Porter, Donald E.; et al(
, ACM Transactions on Storage)
Making logical copies, or clones, of files and directories is critical to many real-world applications and workflows, including backups, virtual machines, and containers. An ideal clone implementation meets the following performance goals: (1) creating the clone has low latency; (2) reads are fast in all versions (i.e., spatial locality is always maintained, even after modifications); (3) writes are fast in all versions; (4) the overall system is space efficient. Implementing a clone operation that realizes all four properties, which we call a nimble clone , is a long-standing open problem. This article describes nimble clones in B-ϵ-tree File System (BetrFS),more »an open-source, full-path-indexed, and write-optimized file system. The key observation behind our work is that standard copy-on-write heuristics can be too coarse to be space efficient, or too fine-grained to preserve locality. On the other hand, a write-optimized key-value store, such as a Bε-tree or an log-structured merge-tree (LSM)-tree, can decouple the logical application of updates from the granularity at which data is physically copied. In our write-optimized clone implementation, data sharing among clones is only broken when a clone has changed enough to warrant making a copy, a policy we call copy-on-abundant-write . We demonstrate that the algorithmic work needed to batch and amortize the cost of BetrFS clone operations does not erode the performance advantages of baseline BetrFS; BetrFS performance even improves in a few cases. BetrFS cloning is efficient; for example, when using the clone operation for container creation, BetrFS outperforms a simple recursive copy by up to two orders-of-magnitude and outperforms file systems that have specialized Linux Containers (LXC) backends by 3--4×.« less
Making logical copies, or clones, of files and directories is critical to many real-world applications and work- flows, including backups, virtual machines, and containers. An ideal clone implementation meets the follow- ing performance goals: (1) creating the clone has low latency; (2) reads are fast in all versions (i.e., spatial locality is always maintained, even after modifications); (3) writes are fast in all versions; (4) the overall sys- tem is space efficient. Implementing a clone operation that realizes all four properties, which we call a nimble clone, is a long-standing open problem. This article describes nimble clones in B-ε-tree Filemore »System (BetrFS), an open-source, full-path-indexed, and write-optimized file system. The key observation behind our work is that standard copy-on-write heuristics can be too coarse to be space efficient, or too fine-grained to preserve locality. On the other hand, a write- optimized key-value store, such as a Bε -tree or an log-structured merge-tree (LSM)-tree, can decouple the logical application of updates from the granularity at which data is physically copied. In our write-optimized clone implementation, data sharing among clones is only broken when a clone has changed enough to warrant making a copy, a policy we call copy-on-abundant-write. We demonstrate that the algorithmic work needed to batch and amortize the cost of BetrFS clone operations does not erode the performance advantages of baseline BetrFS; BetrFS performance even improves in a few cases. BetrFS cloning is efficient; for example, when using the clone operation for container creation, BetrFSoutperforms a simple recursive copy by up to two orders-of-magnitude and outperforms file systems that have specialized Linux Containers (LXC) backends by 3–4×.« less
Jiang, J., Schenck, E., Kranz, S., Banerjee, S., and Banerjee, N. K. CNN-Based Non-contact Detection of Food Level in Bottles from RGB Images. Retrieved from https://par.nsf.gov/biblio/10094310. International Conference on Multimedia Modeling . Web. doi:10.1007/978-3-030-05710-7_17.
Jiang, J., Schenck, E., Kranz, S., Banerjee, S., & Banerjee, N. K. CNN-Based Non-contact Detection of Food Level in Bottles from RGB Images. International Conference on Multimedia Modeling, (). Retrieved from https://par.nsf.gov/biblio/10094310. https://doi.org/10.1007/978-3-030-05710-7_17
@article{osti_10094310,
place = {Country unknown/Code not available},
title = {CNN-Based Non-contact Detection of Food Level in Bottles from RGB Images},
url = {https://par.nsf.gov/biblio/10094310},
DOI = {10.1007/978-3-030-05710-7_17},
abstractNote = {In this paper, we present an approach that detects the level of food in store-bought containers using deep convolutional neural networks (CNNs) trained on RGB images captured using an off-the-shelf camera. Our approach addresses three challenges—the diversity in container geometry, the large variations in shapes and appearances of labels on store-bought containers, and the variability in color of container contents—by augmenting the data used to train the CNNs using printed labels with synthetic textures attached to the training bottles, interchanging the contents of the bottles of the training containers, and randomly altering the intensities of blocks of pixels in the labels and at the bottle borders. Our approach provides an average level detection accuracy of 92.4% using leave-one-out cross-validation on 10 store-bought bottles of varying geometries, label appearances, label shapes, and content colors.},
journal = {International Conference on Multimedia Modeling},
author = {Jiang, J. and Schenck, E. and Kranz, S. and Banerjee, S. and Banerjee, N. K.},
}
