paper-with-me

Papers

Think Twice Before You Act: Improving Inverse Problem Solving With MCMC

2024-09-13 · Yaxuan Zhu, Zehao Dou, Haoxin Zheng, Yasi Zhang, Ying Nian Wu, Ruiqi Gao

Recent studies demonstrate that diffusion models can serve as a strong prior for solving inverse problems. A prominent example is Diffusion Posterior Sampling (DPS), which approximates the posterior distribution of data given the measure using Tweedie's formula. Despite the merits of being versatile in solving various inverse problems without re-training, the performance of DPS is hindered by the fact that this posterior approximation can be inaccurate especially for high noise levels. Therefore, we propose \textbf{D}iffusion \textbf{P}osterior \textbf{MC}MC (\textbf{DPMC}), a novel inference algorithm based on Annealed MCMC to solve inverse problems with pretrained diffusion models. We define a series of intermediate distributions inspired by the approximated conditional distributions used by DPS. Through annealed MCMC sampling, we encourage the samples to follow each intermediate distribution more closely before moving to the next distribution at a lower noise level, and therefore reduce the accumulated error along the path. We test our algorithm in various inverse problems, including super resolution, Gaussian deblurring, motion deblurring, inpainting, and phase retrieval. Our algorithm outperforms DPS with less number of evaluations across nearly all tasks, and is competitive among existing approaches.

📄 PDF Abstract BibTeX arXiv:2409.08551

Code (0)

등록된 구현이 없습니다.

Tasks

DeblurringSuper-Resolution

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

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement

2026-04-02 · Difan Jiao, Qianfeng Wen, Blair Yang, Zhenwei Tang 외 arxiv

We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (GRPO). In each pair of training steps, Th…

Mathematical Reasoning

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation

2025-05-24 · Hong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, Nhien-An Le-Khac

Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either postprocessing manipulations or distrib…

DeepFake DetectionFace SwappingTest-time Adaptation

Think Twice Before Recognizing: Large Multimodal Models for General Fine-grained Traffic Sign Recognition

2024-09-03 · Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda 외

We propose a new strategy called think twice before recognizing to improve fine-grained traffic sign recognition (TSR). Fine-grained TSR in the wild is difficult due to the complex road conditions, and existing approache…

In-Context LearningTraffic Sign Recognition

Think-then-Act: A Dual-Angle Evaluated Retrieval-Augmented Generation

2024-06-18 · Yige Shen, Hao Jiang, Hua Qu, Jihong Zhao

Despite their impressive capabilities, large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content. Enhancing LLMs with retrieval mechanisms to fetch relevant inf…

RetrievalRetrieval-augmented Generation

Think Twice: Branch-and-Rethink Reasoning Reward Model

2025-10-27 · Yizhu Jiao, Jiaqi Zeng, Julien Veron Vialard, Oleksii Kuchaiev 외 arxiv

Large language models (LLMs) increasingly rely on thinking models that externalize intermediate steps and allocate extra test-time compute, with think-twice strategies showing that a deliberate second pass can elicit str…

Reinforcement Learning