paper-with-me

Papers

When Neural Networks Using Different Sensors Create Similar Features

2021-11-04 · Hugues Moreau, Andréa Vassilev, Liming Chen

Multimodal problems are omnipresent in the real world: autonomous driving, robotic grasping, scene understanding, etc... We draw from the well-developed analysis of similarity to provide an example of a problem where neural networks are trained from different sensors, and where the features extracted from these sensors still carry similar information. More precisely, we demonstrate that for each sensor, the linear combination of the features from the last layer that correlates the most with other sensors corresponds to the classification components of the classification layer.

📄 PDF Abstract BibTeX arXiv:2111.02732

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingClassificationRobotic GraspingScene Understanding

Similar Papers 제목 키워드 기반

Let's Get the FACS Straight -- Reconstructing Obstructed Facial Features

2023-11-09 · Tim Büchner, Sven Sickert, Gerd Fabian Volk, Christoph Anders 외

The human face is one of the most crucial parts in interhuman communication. Even when parts of the face are hidden or obstructed the underlying facial movements can be understood. Machine learning approaches often fail …

Style Transfer

Neural Ganglion Sensors: Learning Task-specific Event Cameras Inspired by the Neural Circuit of the Human Retina

2025-04-18 · Haley M. So, Gordon Wetzstein

Inspired by the data-efficient spiking mechanism of neurons in the human eye, event cameras were created to achieve high temporal resolution with minimal power and bandwidth requirements by emitting asynchronous, per-pix…

Optical Flow Estimation

OMCL: Open-vocabulary Monte Carlo Localization

2025-12-17 · Evgenii Kruzhkov, Raphael Memmesheimer, Sven Behnke arxiv

Robust robot localization is an important prerequisite for navigation, but it becomes challenging when the map and robot measurements are obtained from different sensors. Prior methods are often tailored to specific envi…

Point Clouds

Graph-based denoising for time-varying point clouds

2015-11-16 · Yann Schoenenberger, Johan Paratte, Pierre Vandergheynst

Noisy 3D point clouds arise in many applications. They may be due to errors when constructing a 3D model from images or simply to imprecise depth sensors. Point clouds can be given geometrical structure using graphs crea…

DenoisingTime SeriesTime Series Analysis

Player Modeling using Behavioral Signals in Competitive Online Games

2021-11-29 · Arman Dehpanah, Muheeb Faizan Ghori, Jonathan Gemmell, Bamshad Mobasher

Competitive online games use rating systems to match players with similar skills to ensure a satisfying experience for players. In this paper, we focus on the importance of addressing different aspects of playing behavio…