58 citations · 67 across the 12 of their papers we have counts for
12 papers
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
Hao Li, Shamit Lal, Zhiheng Li +9
We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training…
FairRAG: Fair Human Generation via Fair Retrieval Augmentation
Robik Shrestha, Yang Zou, Qiuyu Chen +3
Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where mo…
Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Zeliang Zhang, Mingqian Feng, Zhiheng Li +1
Machine learning models can perform well on in-distribution data but often fail on biased subgroups that are underrepresented in the training data, hindering the robustness of mode…
You Only Need a Good Embeddings Extractor to Fix Spurious Correlations
Raghav Mehta, Vítor Albiero, Li Chen +4
Spurious correlations in training data often lead to robustness issues since models learn to use them as shortcuts. For example, when predicting whether an object is a cow, a model…
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
Zhiheng Li, Ivan Evtimov, Albert Gordo +5
Machine learning models have been found to learn shortcuts -- unintended decision rules that are unable to generalize -- undermining models' reliability. Previous works address thi…
Discover and Mitigate Unknown Biases with Debiasing Alternate Networks
Zhiheng Li, Anthony Hoogs, Chenliang Xu
Deep image classifiers have been found to learn biases from datasets. To mitigate the biases, most previous methods require labels of protected attributes (e.g., age, skin tone) as…
StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis
Zhiheng Li, Martin Renqiang Min, Kai Li +1
Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lac…
Discover the Unknown Biased Attribute of an Image Classifier
Zhiheng Li, Chenliang Xu
Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeli…
Graph Neural Network Based Coarse-Grained Mapping Prediction
Zhiheng Li, Geemi P. Wellawatte, Maghesree Chakraborty +3
The selection of coarse-grained (CG) mapping operators is a critical step for CG molecular dynamics (MD) simulation. It is still an open question about what is optimal for this cho…
Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection
Jie Chen, Zhiheng Li, Jiebo Luo +1
We address weakly-supervised video actor-action segmentation (VAAS), which extends general video object segmentation (VOS) to additionally consider action labels of the actors. The…
Deep Grouping Model for Unified Perceptual Parsing
Zhiheng Li, Wenxuan Bao, Jiayang Zheng +1
The perceptual-based grouping process produces a hierarchical and compositional image representation that helps both human and machine vision systems recognize heterogeneous visual…
Lip Movements Generation at a Glance
Lele Chen, Zhiheng Li, Ross K. Maddox +2
Cross-modality generation is an emerging topic that aims to synthesize data in one modality based on information in a different modality. In this paper, we consider a task of such:…