An official website of the United States government
This paper presents a unified framework to learn to quantify perceptual attributes (e.g., safety, attractiveness) of physical urban environments using crowd-sourced street-view photos without human annotations. The efforts of this work include two folds. First, we collect a large-scale urban image dataset in multiple major cities in U.S.A., which consists of multiple street-view photos for every place. Instead of using subjective annotations as in previous works, which are neither accurate nor consistent, we collect for every place the safety score from government’s crime event records as objective safety indicators. Second, we observe that the place-centric perception task is by nature a multi-instance regression problem since the labels are only available for places (bags), rather than images or image regions (instances). We thus introduce a deep convolutional neural network (CNN) to parameterize the instance-level scoring function, and develop an EM algorithm to alternatively estimate the primary instances (images or image regions) which affect the safety scores and train the proposed network. Our method is capable of localizing interesting images and image regions for each place.We evaluate the proposed method on a newly created dataset and a public dataset. Results with comparisons showed that our method can clearly outperform the alternative perception methods and more importantly, is capable of generating region-level safety scores to facilitate interpretations of the perception process.
more »
« less
This content will become publicly available on May 24, 2026
Trustworthy Contextual Neural Networks for Deciphering Fracture in Metals
ABSTRACT A novel approach was proposed and implemented to assess the confidence of the individual class predictions made by convolutional neural networks trained to identify the type of fracture in metals. This approach involves utilizing contextual evidence in the form of contextual fracture images and contextual scores, which serve as indicators for determining the certainty of the predictions. This approach was first tested on both shallow and deep convolutional neural networks employing four publicly available image datasets: MNIST, EMNIST, FMNIST, and CIFAR10, and subsequently validated on an in‐house steel fracture dataset—FRAC, containing ductile and brittle fracture images. The effectiveness of the method is validated by producing contextual images and scores for the fracture image data and other image datasets to assess the confidence of selected predictions from the datasets. The CIFAR‐10 dataset yielded the lowest mean contextual score of 78 for the shallow model, with over 50% of representative test instances receiving a score below 90, indicating lower confidence in the model's predictions. In contrast, the CNN model used for the fracture dataset achieved a mean contextual score of 99, with 0% of representative test instances receiving a score below 90, suggesting a high level of confidence in its predictions. This approach enhances the interpretability of trained convolutional neural networks and provides greater insight into the confidence of their outputs.
more »
« less
- Award ID(s):
- 2329562
- PAR ID:
- 10592809
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Fatigue & Fracture of Engineering Materials & Structures
- ISSN:
- 8756-758X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Abstract We present improvements over our previous approach to automatic winter hydrometeor classification by means of convolutional neural networks (CNNs), using more data and improved training techniques to achieve higher accuracy on a more complicated dataset than we had previously demonstrated. As an advancement of our previous proof-of-concept study, this work demonstrates broader usefulness of deep CNNs by using a substantially larger and more diverse dataset, which we make publicly available, from many more snow events. We describe the collection, processing, and sorting of this dataset of over 25,000 high-quality multiple-angle snowflake camera (MASC) image chips split nearly evenly between five geometric classes: aggregate, columnar crystal, planar crystal, graupel, and small particle. Raw images were collected over 32 snowfall events between November 2014 and May 2016 near Greeley, Colorado and were processed with an automated cropping and normalization algorithm to yield 224x224 pixel images containing possible hydrometeors. From the bulk set of over 8,400,000 extracted images, a smaller dataset of 14,793 images was sorted by image quality and recognizability (Q&R) using manual inspection. A presorting network trained on the Q&R dataset was applied to all 8,400,000+ images to automatically collect a subset of 283,351 good snowflake images. Roughly 5,000 representative examples were then collected from this subset manually for each of the five geometric classes. With a higher emphasis on in-class variety than our previous work, the final dataset yields trained networks that better capture the imperfect cases and diverse forms that occur within the broad categories studied to achieve an accuracy of 96.2% on a vastly more challenging dataset.more » « less
-
Artificial intelligence (AI) and machine learning models are being increasingly deployed in real-world applications. In many of these applications, there is strong motivation to develop hybrid systems in which humans and AI algorithms can work together, leveraging their complementary strengths and weaknesses. We develop a Bayesian framework for combining the predictions and different types of confidence scores from humans and machines. The framework allows us to investigate the factors that influence complementarity, where a hybrid combination of human and machine predictions leads to better performance than combinations of human or machine predictions alone. We apply this framework to a large-scale dataset where humans and a variety of convolutional neural networks perform the same challenging image classification task. We show empirically and theoretically that complementarity can be achieved even if the human and machine classifiers perform at different accuracy levels as long as these accuracy differences fall within a bound determined by the latent correlation between human and machine classifier confidence scores. In addition, we demonstrate that hybrid human–machine performance can be improved by differentiating between the errors that humans and machine classifiers make across different class labels. Finally, our results show that eliciting and including human confidence ratings improve hybrid performance in the Bayesian combination model. Our approach is applicable to a wide variety of classification problems involving human and machine algorithms.more » « less
-
Implementing local contextual guidance principles in a single-layer CNN architecture, we propose an efficient algorithm for developing broad-purpose representations (i.e., representations transferable to new tasks without additional training) in shallow CNNs trained on limited-size datasets. A contextually guided CNN (CG-CNN) is trained on groups of neighboring image patches picked at random image locations in the dataset. Such neighboring patches are likely to have a common context and therefore are treated for the purposes of training as belonging to the same class. Across multiple iterations of such training on different context-sharing groups of image patches, CNN features that are optimized in one iteration are then transferred to the next iteration for further optimization, etc. In this process, CNN features acquire higher pluripotency, or inferential utility for any arbitrary classification task. In our applications to natural images and hyperspectral images, we find that CG-CNN can learn transferable features similar to those learned by the first layers of the well-known deep networks and produce favorable classification accuracies.more » « less
-
null (Ed.)Nowadays most research in visual recognition using Convolutional Neural Networks (CNNs) follows the “deeper model with deeper confidence” belief to gain a higher recognition accuracy. At the same time, deeper model brings heavier computation. On the other hand, for a large chunk of recognition challenges, a system can classify images correctly using simple models or so-called shallow networks. Moreover, the implementation of CNNs faces with the size, weight, and energy constraints on the embedded devices. In this paper, we implement the adaptive switching between shallow and deep networks to reach the highest throughput on a resource-constrained MPSoC with CPU and FPGA. To this end, we develop and present a novel architecture for the CNNs where a gate makes the decision whether using the deeper model is beneficial or not. Due to resource limitation on FPGA, the idea of partial reconfiguration has been used to accommodate deep CNNs on the FPGA resources. We report experimental results on CIFAR-10, CIFAR-100, and SVHN datasets to validate our approach. Using confidence metric as the decision making factor, only 69.8%, 71.8%, and 43.8% of the computation in the deepest network is done for CIFAR10, CIFAR-100, and SVHN while it can maintain the desired accuracy with the throughput of around 400 images per second for SVHN dataset. https://github.com/mfarhadi/AHCNN.more » « less
