Accurate uncertainty quantification is necessary to enhance the reliability of deep learning (DL) models in realworld applications. In the case of regression tasks, prediction intervals (PIs) should be provided along with the deterministic predictions of DL models. Such PIs are useful or “high-quality (HQ)” as long as they are sufficiently narrow and capture most of the probability density. In this article, we present a method to learn PIs for regression-based neural networks (NNs) automatically in addition to the conventional target predictions. In particular, we train two companion NNs: one that uses one output, the target estimate, and another that uses two outputs, the upper and lower bounds of the corresponding PI. Our main contribution is the design of a novel loss function for the PI-generation network that takes into account the output of the target-estimation network and has two optimization objectives: minimizing the mean PI width and ensuring the PI integrity using constraints that maximize the PI probability coverage implicitly. Furthermore, we introduce a self-adaptive coefficient that balances both objectives within the loss function, which alleviates the task of fine-tuning. Experiments using a synthetic dataset, eight benchmark datasets, and a real-world crop yield prediction dataset showed that our method was able to maintain a nominal probability coverage and produce significantly narrower PIs without detriment to its target estimation accuracy when compared to those PIs generated by three state-of-the-art neuralnetwork-based methods. In other words, our method was shown to produce higher quality PIs.
more »
« less
Keypoint-Based Gaze Tracking
Effective assisted living environments must be able to perform inferences on how their occupants interact with their environment. Gaze direction provides strong indications of how people interact with their surroundings. In this paper, we propose a gaze tracking method that uses a neural network regressor to estimate gazes from keypoints and integrates them over time using a moving average mechanism. Our gaze regression model uses confidence gated units to handle cases of keypoint occlusion and estimate its own prediction uncertainty. Our temporal approach for gaze tracking incorporates these prediction uncertainties as weights in the moving average scheme. Experimental results on a dataset collected in an assisted living facility demonstrate that our gaze regression network performs on par with a complex, dataset-specific baseline, while its uncertainty predictions are highly correlated with the actual angular error of corresponding estimations. Finally, experiments on videos sequences show that our temporal approach generates more accurate and stable gaze predictions.
more »
« less
- Award ID(s):
- 1854158
- NSF-PAR ID:
- 10319946
- Date Published:
- Journal Name:
- International Conference on Pattern Recognition
- Volume:
- 12662
- ISSN:
- 1051-4651
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Advances in visual perceptual tasks have been mainly driven by the amount, and types, of annotations of large-scale datasets. Researchers have focused on fully-supervised settings to train models using offline epoch-based schemes. Despite the evident advancements, limitations and cost of manually annotated datasets have hindered further development for event perceptual tasks, such as detection and localization of objects and events in videos. The problem is more apparent in zoological applications due to the scarcity of annotations and length of videos-most videos are at most ten minutes long. Inspired by cognitive theories, we present a self-supervised perceptual prediction framework to tackle the problem of temporal event segmentation by building a stable representation of event-related objects. The approach is simple but effective. We rely on LSTM predictions of high-level features computed by a standard deep learning backbone. For spatial segmentation, the stable representation of the object is used by an attention mechanism to filter the input features before the prediction step. The self-learned attention maps effectively localize the object as a side effect of perceptual prediction. We demonstrate our approach on long videos from continuous wildlife video monitoring, spanning multiple days at 25 FPS. We aim to facilitate automated ethogramming by detecting and localizing events without the need for labels. Our approach is trained in an online manner on streaming input and requires only a single pass through the video, with no separate training set. Given the lack of long and realistic (includes real-world challenges) datasets, we introduce a new wildlife video dataset–nest monitoring of the Kagu (a flightless bird from New Caledonia)–to benchmark our approach. Our dataset features a video from 10 days (over 23 million frames) of continuous monitoring of the Kagu in its natural habitat. We annotate every frame with bounding boxes and event labels. Additionally, each frame is annotated with time-of-day and illumination conditions. We will make the dataset, which is the first of its kind, and the code available to the research community. We find that the approach significantly outperforms other self-supervised, traditional (e.g., Optical Flow, Background Subtraction) and NN-based (e.g., PA-DPC, DINO, iBOT), baselines and performs on par with supervised boundary detection approaches (i.e., PC). At a recall rate of 80%, our best performing model detects one false positive activity every 50 min of training. On average, we at least double the performance of self-supervised approaches for spatial segmentation. Additionally, we show that our approach is robust to various environmental conditions (e.g., moving shadows). We also benchmark the framework on other datasets (i.e., Kinetics-GEBD, TAPOS) from different domains to demonstrate its generalizability. The data and code are available on our project page:
https://aix.eng.usf.edu/research_automated_ethogramming.html -
We introduce WebGazer, an online eye tracker that uses common webcams already present in laptops and mobile devices to infer the eye-gaze locations of web visitors on a page in real time. The eye tracking model self-calibrates by watching web visitors interact with the web page and trains a mapping between features of the eye and positions on the screen. This approach aims to provide a natural experience to everyday users that is not restricted to laboratories and highly controlled user studies. WebGazer has two key components: a pupil detector that can be combined with any eye detection library, and a gaze estimator using regression analysis informed by user interactions. We perform a large remote online study and a small in-person study to evaluate WebGazer. The findings show that WebGazer can learn from user interactions and that its accuracy is sufficient for approximating the user's gaze. As part of this paper, we release the first eye tracking library that can be easily integrated in any website for real-time gaze interactions, usability studies, or web research.more » « less
-
Traditional models of motor control typically operate in the domain of continuous signals such as spike rates, forces, and kinematics. However, there is growing evidence that precise spike timings encode significant information that coordinates and causally influences motor control. Some existing neural network models incorporate spike timing precision but they neither predict motor spikes coordinated across multiple motor units nor capture sensory-driven modulation of agile locomotor control. In this paper, we propose a visual encoder and model of a sensorimotor system based on a recurrent neural network (RNN) that utilizes spike timing encoding during smooth pursuit target tracking. We use this to predict a nearly complete, spike-resolved motor program of a hawkmoth that requires coordinated millisecond precision across 10 major flight motor units. Each motor unit enervates one muscle and utilizes both rate and timing encoding. Our model includes a motion detection mechanism inspired by the hawkmoth's compound eye, a convolutional encoder that compresses the sensory input, and a simple RNN that is sufficient to sequentially predict wingstroke-to-wingstroke modulation in millisecond-precise spike timings. The two-layer output architecture of the RNN separately predicts the occurrence and timing of each spike in the motor program. The dataset includes spikes recorded from all motor units during a tethered flight where the hawkmoth attends to a moving robotic flower, with a total of roughly 7000 wingstrokes from 16 trials on 5 hawkmoth subjects. Intra-trial and same-subject inter-trial predictions on the test data show that nearly every spike can be predicted within 2 ms of its known spike timing precision values. Whereas, spike occurrence prediction accuracy is about 90%. Overall, our model can predict the precise spike timing of a nearly complete motor program for hawkmoth flight with a precision comparable to that seen in agile flying insects. Such an encoding framework that captures visually-modulated precise spike timing codes and coordination can reveal how organisms process visual cues for agile movements. It can also drive the next generation of neuromorphic controllers for navigation in complex environments.more » « less
-
Agaian, Sos S. ; DelMarco, Stephen P. ; Asari, Vijayan K. (Ed.)Iris recognition is a widely used biometric technology that has high accuracy and reliability in well-controlled environments. However, the recognition accuracy can significantly degrade in non-ideal scenarios, such as off-angle iris images. To address these challenges, deep learning frameworks have been proposed to identify subjects through their off-angle iris images. Traditional CNN-based iris recognition systems train a single deep network using multiple off-angle iris image of the same subject to extract the gaze invariant features and test incoming off-angle images with this single network to classify it into same subject class. In another approach, multiple shallow networks are trained for each gaze angle that will be the experts for specific gaze angles. When testing an off-angle iris image, we first estimate the gaze angle and feed the probe image to its corresponding network for recognition. In this paper, we present an analysis of the performance of both single and multimodal deep learning frameworks to identify subjects through their off-angle iris images. Specifically, we compare the performance of a single AlexNet with multiple SqueezeNet models. SqueezeNet is a variation of the AlexNet that uses 50x fewer parameters and is optimized for devices with limited computational resources. Multi-model approach using multiple shallow networks, where each network is an expert for a specific gaze angle. Our experiments are conducted on an off-angle iris dataset consisting of 100 subjects captured at 10-degree intervals between -50 to +50 degrees. The results indicate that angles that are more distant from the trained angles have lower model accuracy than the angles that are closer to the trained gaze angle. Our findings suggest that the use of SqueezeNet, which requires fewer parameters than AlexNet, can enable iris recognition on devices with limited computational resources while maintaining accuracy. Overall, the results of this study can contribute to the development of more robust iris recognition systems that can perform well in non-ideal scenarios.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/978-3-030-68790-8_12
