KLIEP-based Density Ratio Estimation for Semantically Consistent Synthetic to Real Images Adaptation in Urban Traffic Scenes
Synthetic data has been applied in many deep learning based computer vision tasks. Limited performance of algorithms trained solely on synthetic data has been approached with domain adaptation techniques such as the ones based on generative adversarial framework. We demonstrate how adversarial training alone can introduce semantic inconsistencies in translated images. To tackle this issue we propose density prematching strategy using KLIEP-based density ratio estimation procedure. Finally, we show that aforementioned strategy improves quality of translated images of underlying method and their usability for the semantic segmentation task in the context of autonomous driving.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingDensity Ratio EstimationDomain AdaptationSemantic SegmentationSimilar Papers 제목 키워드 기반
Density Ratio Estimation and Neyman Pearson Classification with Missing Data
Density Ratio Estimation (DRE) is an important machine learning technique with many downstream applications. We consider the challenge of DRE with missing not at random (MNAR) data. In this setting, we show that using st…
Density Ratio EstimationImproving importance estimation in covariate shift for providing accurate prediction error
In traditional Machine Learning, the algorithms predictions are based on the assumption that the data follows the same distribution in both the training and the test datasets. However, in real world data this condition d…
Density EstimationInvestigating the Adversarial Robustness of Density Estimation Using the Probability Flow ODE
Beyond their impressive sampling capabilities, score-based diffusion models offer a powerful analysis tool in the form of unbiased density estimation of a query sample under the training data distribution. In this work, …
Adversarial RobustnessDensity EstimationDensity-Aware Translation of Spurious Correlations in Zero-Shot VLMs
Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification. However, their predictions remain sensitive to spurious correlations, where contextual cues dominate over semantic content. Earlier …
Prompt EngineeringDouble Debiased Covariate Shift Adaptation Robust to Density-Ratio Estimation
Consider a scenario where we have access to train data with both covariates and outcomes while test data only contains covariates. In this scenario, our primary aim is to predict the missing outcomes of the test data. Wi…
Density Ratio Estimationregression