| Presentation | 2012-11-07 No Bias Left Behind : Covariate Shift Adaptation for Discriminative 3D Pose Estimation Makoto YAMADA, Leonid SIGAL, Michalis RAPTIS, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Discriminative, or (structured) prediction, methods have proved effective for variety of problems in computer vision; a notable example is 3D monocular pose estimation. All methods to date, however, relied on an assumption that training (source) and test (target) data come from the same underlying joint distribution. In many real cases, including standard datasets, this assumption is flawed. In presence of training set bias, the learning results in a biased model whose performance degrades on the (target) test set. Under the assumption of covariate shift we propose an unsupervised domain adaptation approach to address this problem. The approach takes the form of training instance re-weighting, where the weights are assigned based on the ratio of training and test marginals evaluated at the samples. Learning with the resulting weighted training samples, alleviates the bias in the learned models. We show the efficacy of our approach by proposing weighted variants of Kernel Regression (KR) and Twin Gaussian Processes (TGP). We show that our weighted variants outperform their un-weighted counterparts and improve on the state-of-the-art performance in the public (HUMANEVA) dataset. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Pose estimation / covariate shift adaptation / RuLSIF / twin Gaussian Processes |
| Paper # | IBISML2012-34 |
| Date of Issue |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2012/10/31(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Information-Based Induction Sciences and Machine Learning (IBISML) |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | No Bias Left Behind : Covariate Shift Adaptation for Discriminative 3D Pose Estimation |
| Sub Title (in English) | |
| Keyword(1) | Pose estimation |
| Keyword(2) | covariate shift adaptation |
| Keyword(3) | RuLSIF |
| Keyword(4) | twin Gaussian Processes |
| 1st Author's Name | Makoto YAMADA |
| 1st Author's Affiliation | NTT Communication Science Laboratories() |
| 2nd Author's Name | Leonid SIGAL |
| 2nd Author's Affiliation | Disney Research Pittsburgh |
| 3rd Author's Name | Michalis RAPTIS |
| 3rd Author's Affiliation | Disney Research Pittsburgh |
| Date | 2012-11-07 |
| Paper # | IBISML2012-34 |
| Volume (vol) | vol.112 |
| Number (no) | 279 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |