Related papers: Scalable Full Flow with Learned Binary Descriptors
We study cost-aware routing for large language models across diverse and dynamic pools of models. Existing approaches often overlook prompt-specific context, rely on expensive model profiling, assume a fixed set of experts, or use…
Deep learning-based video surveillance increasingly demands privacy-preserving architectures with low computational and environmental overhead. Federated learning preserves privacy but deploying large vision-language models (VLMs)…
Optical flow is a regression task where convolutional neural networks (CNNs) have led to major breakthroughs. However, this comes at major computational demands due to the use of cost-volumes and pyramidal representations. This was…
We present a method enabling the scaling of NeRFs to learn a large number of semantically-similar scenes. We combine two techniques to improve the required training time and memory cost per scene. First, we learn a 3D-aware latent space in…
Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to…
Federated learning (FL) is a privacy-preserving machine learning setting that enables many devices to jointly train a shared global model without the need to reveal their data to a central server. However, FL involves a frequent exchange of…
Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity. We propose a neuroevolution method capable of evolving and optimizing CNNs with respect to the…
Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…
In recent years, Convolutional Neural Networks (CNNs) have enabled ubiquitous image processing applications. As such, CNNs require fast runtime (forward propagation) to process high-resolution visual streams in real time. This is still a…
Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segmentation is the problem of simultaneous segmentation and…
Data association problems are an important component of many computer vision applications, with multi-object tracking being one of the most prominent examples. A typical approach to data association involves finding a graph matching or…
We describe a novel approach to image based localisation in urban environments using semantic matching between images and a 2-D map. It contrasts with the vast majority of existing approaches which use image to image database matching. We…
Deep-learning methods have shown promising performance for low-dose computed tomography (LDCT) reconstruction. However, supervised methods face the problem of lacking labeled data in clinical scenarios, and the CNN-based unsupervised…
We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our…
During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving and augmented reality. However, to train CNNs…
Deep learning models operating in the complex domain are used due to their rich representation capacity. However, most of these models are either restricted to the first quadrant of the complex plane or project the complex-valued data into…
Convolutional neural networks(CNN) have been shown to perform better than the conventional stereo algorithms for stereo estimation. Numerous efforts focus on the pixel-wise matching cost computation, which is the important building block…
State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two…
Binarized neural networks (BNNs) are gaining interest in the deep learning community due to their significantly lower computational and memory cost. They are particularly well suited to reconfigurable logic devices, which contain an…
Convolutional neural network (CNN) slides a kernel over the whole image to produce an output map. This kernel scheme reduces the number of parameters with respect to a fully connected neural network (NN). While CNN has proven to be an…