Goto

Collaborating Authors

University of North Carolina, Chapel Hill


Beyond IID: Learning to Combine Non-IID Metrics for Vision Tasks

AAAI Conferences

Metric learning has been widely employed, especially in various computer vision tasks, with the fundamental assumption that all samples (e.g., regions/superpixels in images/videos) are independent and identically distributed (IID). However, since the samples are usually spatially-connected or temporally-correlated with their physically-connected neighbours, they are not IID (non-IID for short), which cannot be directly handled by existing methods. Thus, we propose to learn and integrate non-IID metrics (NIME). To incorporate the non-IID spatial/temporal relations, instead of directly using non-IID features and metric learning as previous methods, NIME first builds several non-IID representations on original (non-IID) features by various graph kernel functions, and then automatically learns the metric under the best combination of various non-IID representations. NIME is applied to solve two typical computer vision tasks: interactive image segmentation and histology image identification. The results show that learning and integrating non-IID metrics improves the performance, compared to the IID methods. Moreover, our method achieves results comparable or better than that of the state-of-the-arts.


Kulharia

AAAI Conferences

Understanding object motions and transformations is a core problem in computer science. Modeling sequences of evolving images may provide better representations and models of motion and may ultimately be used for forecasting or simulation. Diagrammatic Abstract Reasoning is an avenue in which diagrams evolve in complex patterns and one needs to infer the underlying pattern sequence and generate the next image in the sequence. For this, we develop a novel Contextual Generative Adversarial Network based on Recurrent Neural Networks (Context-RNN-GANs), where both the generator and the discriminator modules are based on contextual history and the adversarial discriminator guides the generator to produce realistic images for the particular time step in the image sequence. We employ the Context-RNN-GAN model (and its variants) on a novel dataset of Diagrammatic Abstract Reasoning as well as perform initial evaluations on a next-frame prediction task of videos. Empirically, we show that our Context-RNN-GAN model performs competitively with 10th-grade human performance but there is still scope for interesting improvements as compared to college-grade human performance.


Shi

AAAI Conferences

Metric learning has been widely employed, especially in various computer vision tasks, with the fundamental assumption that all samples (e.g., regions/superpixels in images/videos) are independent and identically distributed (IID). However, since the samples are usually spatially-connected or temporally-correlated with their physically-connected neighbours, they are not IID (non-IID for short), which cannot be directly handled by existing methods. Thus, we propose to learn and integrate non-IID metrics (NIME). To incorporate the non-IID spatial/temporal relations, instead of directly using non-IID features and metric learning as previous methods, NIME first builds several non-IID representations on original (non-IID) features by various graph kernel functions, and then automatically learns the metric under the best combination of various non-IID representations. NIME is applied to solve two typical computer vision tasks: interactive image segmentation and histology image identification.


Contextual RNN-GANs for Abstract Reasoning Diagram Generation

AAAI Conferences

Understanding object motions and transformations is a core problem in computer science. Modeling sequences of evolving images may provide better representations and models of motion and may ultimately be used for forecasting or simulation. Diagrammatic Abstract Reasoning is an avenue in which diagrams evolve in complex patterns and one needs to infer the underlying pattern sequence and generate the next image in the sequence. For this, we develop a novel Contextual Generative Adversarial Network based on Recurrent Neural Networks (Context-RNN-GANs), where both the generator and the discriminator modules are based on contextual history and the adversarial discriminator guides the generator to produce realistic images for the particular time step in the image sequence. We employ the Context-RNN-GAN model (and its variants) on a novel dataset of Diagrammatic Abstract Reasoning as well as perform initial evaluations on a next-frame prediction task of videos. Empirically, we show that our Context-RNN-GAN model performs competitively with 10th-grade human performance but there is still scope for interesting improvements as compared to college-grade human performance.


Facebook, Youth and Privacy in Networked Publics

AAAI Conferences

Media accounts would have us believe that today’s youth are a particularly narcissistic generation. Young adults are often portrayed as exhibitionists who share personal information excessively and only react if “burned” by experience. This paper reports results from 450 surveys of young adults on social network site usage and privacy and surveillance experiences--as well as from a historical archive dating back to 2006. The findings show a complex picture of a generation actively engaging visibility and social boundaries online through privacy and visibility practices. A striking increase in privacy protective activities is documented. I examine whether these changes are in response to personal negative experiences from online disclosure or if they derive from general awareness. I find that students are reacting pro-actively and adjusting their privacy settings above and beyond the impact of negative personal experiences. Contrary to media reports, young adults do not appear uncaring about privacy and are not waiting until they get burned. Significant racial and gender differences remain in privacy behaviors. Strikingly, about 20% report having deactivated their profile at least once.


g-Planner: Real-time Motion Planning and Global Navigation using GPUs

AAAI Conferences

We present novel randomized algorithms for solving global motion planning problems that exploit the computational capabilities of many-core GPUs. Our approach uses thread and data parallelism to achieve high performance for all components of sample-based algorithms, including random sampling, nearest neighbor computation, local planning, collision queries and graph search. The approach can efficiently solve both the multi-query and single-query versions of the problem and obtain considerable speedups over prior CPU-based algorithms. We demonstrate the efficiency of our algorithms by applying them to a number of 6DOF planning benchmarks in 3D environments. Overall, this is the first algorithm that can perform real-time motion planning and global navigation using commodity hardware.


Pan

AAAI Conferences

We present novel randomized algorithms for solving global motion planning problems that exploit the computational capabilities of many-core GPUs. Our approach uses thread and data parallelism to achieve high performance for all components of sample-based algorithms, including random sampling, nearest neighbor computation, local planning, collision queries and graph search. The approach can efficiently solve both the multi-query and single-query versions of the problem and obtain considerable speedups over prior CPU-based algorithms. We demonstrate the efficiency of our algorithms by applying them to a number of 6DOF planning benchmarks in 3D environments. Overall, this is the first algorithm that can perform real-time motion planning and global navigation using commodity hardware.


Pan

AAAI Conferences

Many task execution techniques tend to repeatedly invoke motion planning algorithms in order to perform complex tasks. In order to accelerate the perform of such methods, we present a real-time global motion planner that utilizes the computational capabilities of current many-core GPUs (graphics processing units). Our approach is based on randomized sample-based planners and we describe highly parallel algorithms to generate samples, perform collision queries, nearest-neighbor computations, local planning and graph search to compute collision-free paths for rigid robots. Our approach can efficiently solve the single-query and multiquery versions of the planning problem and can obtain one to two orders of speedup over prior CPU-based global planning algorithms. The resulting GPU-based planning algorithm can also be used for real-time feedback for task execution in challenging scenarios.


Closing the Loop between Motion Planning and Task Execution Using Real-Time GPU-Based Planners

AAAI Conferences

Many task execution techniques tend to repeatedly invoke motion planning algorithms in order to perform complex tasks. In order to accelerate the perform of such methods, we present a real-time global motion planner that utilizes the computational capabilities of current many-core GPUs (graphics processing units). Our approach is based on randomized sample-based planners and we describe highly parallel algorithms to generate samples, perform collision queries, nearest-neighbor computations, local planning and graph search to compute collision-free paths for rigid robots. Our approach can efficiently solve the single-query and multiquery versions of the planning problem and can obtain one to two orders of speedup over prior CPU-based global planning algorithms. The resulting GPU-based planning algorithm can also be used for real-time feedback for task execution in challenging scenarios.