← Search

Chengzhi Shi

3 accepted papers

2025

H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition

NeurIPS 2025poster

We introduce H-SPLID, a novel algorithm for learning salient feature representations through the explicit decomposition of salient and non-salient features into separate spaces. We show that H-SPLID promotes learning low-dimensional, task-relevant features. We prove that the expected prediction devi…

Cited by 0SourceScholar
2025

Neural Point Processes for Pixel-wise Regression

AISTATS 2025poster

We study pixel-wise regression problems with sparsely annotated images. Traditional regression methods based on mean squared error emphasize pixels with labels, leading to distorted predictions in unlabeled areas. To address this limitation, we introduce Neural Point Processes, a novel approach that…

Cited by 0SourceScholar