Multi-View Networks for Denoising of Arbitrary Numbers of Channels
We propose a set of denoising neural networks capable of operating on an arbitrary number of channels at runtime, irrespective of how many channels they were trained on. We coin the proposed models multi-view networks since they operate using multiple views of the same data. We explore two such architectures and show how they outperform traditional denoising models in multi-channel scenarios. Additionally, we demonstrate how multi-view networks can leverage information provided by additional recordings to make better predictions, and how they are able to generalize to a number of recordings not seen in training.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingSimilar Papers 제목 키워드 기반
Object-centric Denoising Diffusion Models for Physical Reasoning
Reasoning about the trajectories of multiple, interacting objects is integral to physical reasoning tasks in machine learning. This involves conditions imposed on the objects at different time steps, for instance initial…
Reinforcement LearningLearning Canonical View Representation for 3D Shape Recognition with Arbitrary Views
In this paper, we focus on recognizing 3D shapes from arbitrary views, i.e., arbitrary numbers and positions of viewpoints. It is a challenging and realistic setting for view-based 3D shape recognition. We propose a cano…
3D Shape Recognition3D Shape RepresentationAlign and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View Combinations
Multimodal multiview learning seeks to integrate information from diverse sources to enhance task performance. Existing approaches often struggle with flexible view configurations, including arbitrary view combinations, …
Human Activity RecognitionRepresentation LearningContrastive LearningDenoising Task Routing for Diffusion Models
Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL). Despite the inherent connection between diffusion models and …
DenoisingMulti-Task LearningGraph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers
Automatic transcription of meetings requires handling of overlapped speech, which calls for continuous speech separation (CSS) systems. The uPIT criterion was proposed for utterance-level separation with neural networks …
Speech Separation