← Search

Lixuan Yi

2 accepted papers

2019

Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting

NeurIPS 2019poster

Current deep neural networks(DNNs) can easily overfit to biased training data with corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to alleviate this issue by designing a weighting function mapping from training loss to sample weight, and then iterating between weig…

2017

Should We Encode Rain Streaks in Video as Deterministic or Stochastic?

ICCV 2017poster

Videos taken in the wild sometimes contain unexpected rain streaks, which brings difficulty in subsequent video processing tasks. Rain streak removal in a video (RSRV) is thus an important issue and has been attracting much attention in computer vision. Different from previous RSRV methods formulati…

Cited by 162PDFScholar