More Like this

1. Utilizing Transfer Learning, Graph Matching, and Spatial Attention with CARLA Pre-trained Models.

   Iyer, V; Ternovskiy, Igor (November 2024, Springer https://doi.org/10.1007/978-3-031-73125-9_6)

   Arai, Igor (Ed.)

   This research explores practical applications of Transfer Learning and Spatial Attention mechanisms using pre-trained models from an open-source simulator, CARLA (Car Learning to Act). The study focuses on vehicle tracking using aerial images, utilizing transformers and graph algorithms for keypoint detection. The proposed detector training process optimizes model parameters without heavy reliance on manually set hyperparameters. The loss function considers both class distribution and position localization of ground truth data. The study utilizes a three-stage methodology: pre-trained model selection, fine-tuning with a custom synthetic dataset, and evaluation using real-world aerial datasets. The results demonstrate the effectiveness of our synthetic transformer-based transfer learning technique in enhancing object detection accuracy and localization. When tested with real-world images, our approach achieved an 88% detection, compared to only 30% when using YOLOv8. The findings underscore the advantages of incorporating graph-based loss functions in transfer learning and position-encoding techniques, demonstrating their effectiveness in realistic machine learning applications with unbalanced classes. 

   more » « less
2. Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D Learning

   Feng, Qiaojun; Atanasov, Nikolay (January 2021, IEEE International Conference on Robotics and Automation)

   null (Ed.)

   This paper addresses outdoor terrain mapping using overhead images obtained from an unmanned aerial vehicle. Dense depth estimation from aerial images during flight is challenging. While feature-based localization and mapping techniques can deliver real-time odometry and sparse points reconstruction, a dense environment model is generally recovered offline with significant computation and storage. This paper develops a joint 2D-3D learning approach to reconstruct local meshes at each camera keyframe, which can be assembled into a global environment model. Each local mesh is initialized from sparse depth measurements. We associate image features with the mesh vertices through camera projection and apply graph convolution to refine the mesh vertices based on joint 2-D reprojected depth and 3-D mesh supervision. Quantitative and qualitative evaluations using real aerial images show the potential of our method to support environmental monitoring and surveillance applications. 

   more » « less
3. Degradation learning and Skip-Transformer for blind face restoration

   https://doi.org/10.3389/frsip.2023.1106465  

   Cheikh Sidiya, Ahmed; Xu, Xuan; Xu, Ning; Li, Xin (May 2023, Frontiers in Signal Processing)

   Blindrestoration of low-quality faces in the real world has advanced rapidly in recent years. The rich and diverse priors encapsulated by pre-trained face GAN have demonstrated their effectiveness in reconstructing high-quality faces from low-quality observations in the real world. However, the modeling of degradation in real-world face images remains poorly understood, affecting the property of generalization of existing methods. Inspired by the success of pre-trained models and transformers in recent years, we propose to solve the problem of blind restoration by jointly exploiting their power for degradation and prior learning, respectively. On the one hand, we train a two-generator architecture for degradation learning to transfer the style of low-quality real-world faces to the high-resolution output of pre-trained StyleGAN. On the other hand, we present a hybrid architecture, called Skip-Transformer (ST), which combines transformer encoder modules with a pre-trained StyleGAN-based decoder using skip layers. Such a hybrid design is innovative in that it represents the first attempt to jointly exploit the global attention mechanism of the transformer and pre-trained StyleGAN-based generative facial priors. We have compared our DL-ST model with the latest three benchmarks for blind image restoration (DFDNet, PSFRGAN, and GFP-GAN). Our experimental results have shown that this work outperforms all other competing methods, both subjectively and objectively (as measured by the Fréchet Inception Distance and NIQE metrics). 

   more » « less
4. Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems

   https://doi.org/10.1145/3654703  

   Nguyen, Viet Dung; Bailey, Reynold; Diaz, Gabriel J; Ma, Chengyi; Fix, Alexander; Ororbia, Alexander (May 2024, Proceedings of the ACM on Computer Graphics and Interactive Techniques)

   Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. Segmentation models trained using supervised machine learning can excel at this task, their effectiveness is determined by the degree of overlap between the narrow distributions of image properties defined by the target dataset and highly specific training datasets, of which there are few. Attempts to broaden the distribution of existing eye image datasets through the inclusion of synthetic eye images have found that a model trained on synthetic images will often fail to generalize back to real-world eye images. In remedy, we use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data, and to prune the training dataset in a manner that maximizes distribution overlap. We demonstrate that our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples. 

   more » « less
5. Transfer Learning on Small Datasets for Improved Fall Detection

   https://doi.org/10.3390/s23031105  

   Maray, Nader; Ngu, Anne Hee; Ni, Jianyuan; Debnath, Minakshi; Wang, Lu (February 2023, Sensors)

   Falls in the elderly are associated with significant morbidity and mortality. While numerous fall detection devices incorporating AI and machine learning algorithms have been developed, no known smartwatch-based system has been used successfully in real-time to detect falls for elderly persons. We have developed and deployed a SmartFall system on a commodity-based smartwatch which has been trialled by nine elderly participants. The system, while being usable and welcomed by the participants in our trials, has two serious limitations. The first limitation is the inability to collect a large amount of personalized data for training. When the fall detection model, which is trained with insufficient data, is used in the real world, it generates a large amount of false positives. The second limitation is the model drift problem. This means an accurate model trained using data collected with a specific device performs sub-par when used in another device. Therefore, building one model for each type of device/watch is not a scalable approach for developing smartwatch-based fall detection system. To tackle those issues, we first collected three datasets including accelerometer data for fall detection problem from different devices: the Microsoft watch (MSBAND), the Huawei watch, and the meta-sensor device. After that, a transfer learning strategy was applied to first explore the use of transfer learning to overcome the small dataset training problem for fall detection. We also demonstrated the use of transfer learning to generalize the model across the heterogeneous devices. Our preliminary experiments demonstrate the effectiveness of transfer learning for improving fall detection, achieving an F1 score higher by over 10% on average, an AUC higher by over 0.15 on average, and a smaller false positive prediction rate than the non-transfer learning approach across various datasets collected using different devices with different hardware specifications. 

   more » « less