These models typically employ localized attention mechanisms, such as the sliding-window Neighborhood Attention (NA) or Swin Transformer's Shifted Window Self Attention.
Ranked #28 on Semantic Segmentation on ADE20K
Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly.
Given that intrinsic decomposition is a fundamentally ambiguous and under-constrained inverse problem, we propose a novel distance-aware point sampling and adaptive reflectance iterative clustering optimization method that enables IntrinsicNeRF with traditional intrinsic decomposition constraints to be trained in an unsupervised manner, resulting in temporally consistent intrinsic decomposition results.
Given the inherent cost and scarcity of in-domain, task-specific robot data, learning from large, diverse, offline human videos has emerged as a promising path towards acquiring a generally useful visual representation for control; however, how these human videos can be used for general-purpose reward learning remains an open question.
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet.
Ranked #1 on Speech Recognition on CHiME6
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
It provides two base algorithms: the first is based on the convex surrogate loss function from the seminal work of Elmachtoub & Grigas (2021), and the second is based on the differentiable black-box solver approach of Vlastelica et al. (2019).