Related papers: FlashFPS: Efficient Farthest Point Sampling for La…
Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction. However,they usually suffer from two critical issues: (1)fixed upsampling rate after one-time…
Skeleton-based Graph Convolutional Networks (GCNs) models for action recognition have achieved excellent prediction accuracy in the field. However, limited by large model and computation complexity, GCNs for action recognition like 2s-AGCN…
We propose an application of online hard sample mining for efficient training of Neural Radiance Fields (NeRF). NeRF models produce state-of-the-art quality for many 3D reconstruction and rendering tasks but require substantial…
Gradient-based hyperparameter optimization has earned a widespread popularity in the context of few-shot meta-learning, but remains broadly impractical for tasks with long horizons (many gradient steps), due to memory scaling and gradient…
The last few years have seen gigantic leaps in algorithms and systems to support efficient deep learning inference. Pruning and quantization algorithms can now consistently compress neural networks by an order of magnitude. For a compressed…
Point cloud capture processes are error-prone and introduce noisy artifacts that necessitate filtering/denoising. Recent filtering methods often suffer from point clustering or noise retaining issues. In this paper, we propose Hybrid Point…
Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring it to a downstream task. Recently, projected gradient…
In order to retain more feature information of local areas on a point cloud, local grouping and subsampling are the necessary data structuring steps in most hierarchical deep learning models. Due to the disorder nature of the points in a…
While commodity GPUs provide a continuously growing range of features and sophisticated methods for accelerating compute jobs, many state-of-the-art solutions for point cloud rendering still rely on the provided point primitives (GL_POINTS,…
Sliding window convolutional networks (ConvNets) have become a popular approach to computer vision problems such as image segmentation, and object detection and localization. Here we consider the problem of inference, the application of a…
Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance challenges, and voxel-based methods that achieve high…
This research embarks on pioneering the integration of gradient sampling optimization techniques, particularly StochGradAdam, into the pruning process of neural networks. Our main objective is to address the significant challenge of…
Neural architecture search (NAS) is a promising technique to design efficient and high-performance deep neural networks (DNNs). As the performance requirements of ML applications grow continuously, the hardware accelerators start playing a…
Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources to train…
Pruning neural networks has proven to be a successful approach to increase the efficiency and reduce the memory storage of deep learning models without compromising performance. Previous literature has shown that it is possible to achieve a…
With the fast growth of parameter size, it becomes increasingly challenging to deploy large generative models as they typically require large GPU memory consumption and massive computation. Unstructured model pruning has been a common…
Neural network pruning is an essential technique for reducing the size and complexity of deep neural networks, enabling large-scale models on devices with limited resources. However, existing pruning approaches heavily rely on training data…
The rapid development of deep neural networks (DNNs) is inherently accompanied by the problem of high computational costs. To tackle this challenge, dynamic voltage frequency scaling (DVFS) is emerging as a promising technology for…
Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy in stereo matching than traditional…
In this work we propose 3D-FFS, a novel approach to make sensor fusion based 3D object detection networks significantly faster using a class of computationally inexpensive heuristics. Existing sensor fusion based networks generate 3D region…