paper-with-me

홈 › Papers

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

2024-05-29 · Justin Deschenaux, Igor Krawczuk, Grigorios Chrysos, Volkan Cevher

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs trained on strictly separate subsets of the data distribution with large gaps on the support of the latent factors. We show that such a model can effectively generate images in the unexplored, intermediate regions of the distribution. For instance, when trained on clearly smiling and non-smiling faces, we demonstrate a sampling procedure which can generate slightly smiling faces without reference images (zero-shot interpolation). We replicate these findings for other attributes as well as other datasets. Our code is available at https://github.com/jdeschena/ddpm-zero-shot-interpolation.

📄 PDF Abstract BibTeX arXiv:2405.19201

Code (1)

jdeschena/ddpm-zero-shot-interpolation 공식 구현 pytorch

Tasks

DenoisingImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Learning Attention Propagation for Compositional Zero-Shot Learning

2022-10-20 · Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc van Gool, Alain Pagani 외

Compositional zero-shot learning aims to recognize unseen compositions of seen visual primitives of object classes and their states. While all primitives (states and objects) are observable during training in some combin…

Compositional Zero-Shot LearningZero-Shot Learning

Assessing the capacity of a denoising diffusion probabilistic model to reproduce spatial context

2023-09-19 · Rucha Deshpande, Muzaffer Özbey, Hua Li, Mark A. Anastasio 외

Diffusion models have emerged as a popular family of deep generative models (DGMs). In the literature, it has been claimed that one class of diffusion models -- denoising diffusion probabilistic models (DDPMs) -- demonst…

Data AugmentationDenoisingImage Generation

Denoising Diffusion Implicit Models

2020-10-06 · ICLR 2021 1 · Jiaming Song, Chenlin Meng, Stefano Ermon

Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate samp…

DenoisingImage Generation

Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning

2024-01-01 · CVPR 2024 1 · Nirat Saini, Khoi Pham, Abhinav Shrivastava

Learning from seen attribute-object pairs to generalize to unseen compositions has been studied extensively in Compositional Zero-Shot Learning (CZSL). However CZSL setup is still limited to seen attributes and objec…

AttributeCompositional Zero-Shot LearningZero-Shot Learning

Learning to Plan & Schedule with Reinforcement-Learned Bimanual Robot Skills

2025-10-29 · Weikang Wan, Fabio Ramos, Xuning Yang, Caelan Garrett arxiv

Long-horizon contact-rich bimanual manipulation presents a significant challenge, requiring complex coordination involving a mixture of parallel execution and sequential collaboration between arms. In this paper, we intr…

Reinforcement Learning