FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation

2023-12-28 · Miaojie Feng, Longliang Liu, Hao Jia, Gangwei Xu, Xin Yang

Collecting real-world optical flow datasets is a formidable challenge due to the high cost of labeling. A shortage of datasets significantly constrains the real-world performance of optical flow models. Building virtual datasets that resemble real scenarios offers a potential solution for performance enhancement, yet a domain gap separates virtual and real datasets. This paper introduces FlowDA, an unsupervised domain adaptive (UDA) framework for optical flow estimation. FlowDA employs a UDA architecture based on mean-teacher and integrates concepts and techniques in unsupervised optical flow estimation. Furthermore, an Adaptive Curriculum Weighting (ACW) module based on curriculum learning is proposed to enhance the training effectiveness. Experimental outcomes demonstrate that our FlowDA outperforms state-of-the-art unsupervised optical flow estimation method SMURF by 21.6%, real optical flow dataset generation method MPI-Flow by 27.8%, and optical flow estimation adaptive method FlowSupervisor by 30.9%, offering novel insights for enhancing the performance of optical flow estimation in real-world scenarios. The code will be open-sourced after the publication of this paper.

📄 PDF Abstract BibTeX arXiv:2312.16995

Code (0)

등록된 구현이 없습니다.

Tasks

Dataset GenerationOptical Flow Estimation

Generalized Universal Domain Adaptation with Generative Flow Networks

2023-05-08 · Didi Zhu, Yinchuan Li, Yunfeng Shao, Jianye Hao 외

We introduce a new problem in unsupervised domain adaptation, termed as Generalized Universal Domain Adaptation (GUDA), which aims to achieve precise prediction of all target labels including unknown categories. GUDA bri…

Domain Adaptation Universal Domain Adaptation Unsupervised Domain Adaptation

FlowDA: Accurate, Low-Latency Weather Data Assimilation via Flow Matching

2026-02-06 · Ran Cheng, Lailai Zhu arxiv

Data assimilation (DA) is a fundamental component of modern weather prediction, yet it remains a major computational bottleneck in machine learning (ML)-based forecasting pipelines due to reliance on traditional variatio…

FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space

2026-07-09 · Michael Murray, Daphne Chen, Simran Bagaria, Dean Fortier 외 arxiv

Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments routinely expose failure modes outside the …

Reinforcement Learning

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

2025-01-13 · Siyi Chen, Yixuan Jia, Qing Qu, He Sun 외

Data assimilation (DA) integrates observations with a dynamical model to estimate states of PDE-governed systems. Model-driven methods (e.g., Kalman, particle) presuppose full knowledge of the true dynamics, which is not…

State Estimation Super-Resolution Weather Forecasting

Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow

2023-03-24 · Hanyu Zhou, Yi Chang, Gang Chen, Luxin Yan

Optical flow estimation has made great progress, but usually suffers from degradation under adverse weather. Although semi/full-supervised methods have made good attempts, the domain shift between the synthetic and real …

Domain Adaptation Optical Flow Estimation