Joint Manifold Diffusion for Combining Predictions on Decoupled Observations
We present a new predictor combination algorithm that improves a given task predictor based on potentially relevant reference predictors. Existing approaches are limited in that, to discover the underlying task dependence, they either require known parametric forms of all predictors or access to a single fixed dataset on which all predictors are jointly evaluated. To overcome these limitations, we design a new non-parametric task dependence estimation procedure that automatically aligns evaluations of heterogeneous predictors across disjoint feature sets. Our algorithm is instantiated as a robust manifold diffusion process that jointly refines the estimated predictor alignments and the corresponding task dependence. We apply this algorithm to the relative attributes ranking problem and demonstrate that it not only broadens the application range of predictor combination approaches but also outperforms existing methods even when applied to classical predictor combination settings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
From a Bayesian perspective, score-based diffusion solves inverse problems through joint inference, embedding the likelihood with the prior to guide the sampling process. However, this formulation fails to explain its pr…
Computational EfficiencyImage RestorationDecoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation
We propose Decoupled Residual Denoising Diffusion models (DRDD) for unified and data-efficient image-to-image (I2I) translation. While diffusion models have advanced I2I translation in terms of quality and diversity, we …
Image-to-Image TranslationMoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds
Incorporating temporal information effectively is important for accurate 3D human motion estimation and generation which have wide applications from human-computer interaction to AR/VR. In this paper, we present MoManifo…
DenoisingHuman DynamicsMotion Estimationmotion in-betweeningDecoupled Diffusion Sampling for Inverse Problems on Function Spaces
We propose a data-efficient, physics-aware generative framework in function space for inverse PDE problems. Existing plug-and-play diffusion posterior samplers represent physics implicitly through joint coefficient-solut…
Modular Jump Gaussian Processes
Gaussian processes (GPs) furnish accurate nonlinear predictions with well-calibrated uncertainty. However, the typical GP setup has a built-in stationarity assumption, making it ill-suited for modeling data from processe…
Gaussian Processes