216 citations · 802 across the 61 of their papers we have counts for
6 papers · 1 filter
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…
Learning to Answer Questions in Dynamic Audio-Visual Scenarios
Guangyao Li, Yake Wei, Yapeng Tian +3
In this paper, we focus on the Audio-Visual Question Answering (AVQA) task, which aims to answer questions regarding different visual objects, sounds, and their associations in vid…
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…
Transformer-empowered Multi-scale Contextual Matching and Aggregation for Multi-contrast MRI Super-resolution
Guangyuan Li, Jun Lv, Yapeng Tian +4
Magnetic resonance imaging (MRI) can present multi-contrast images of the same anatomical structures, enabling multi-contrast super-resolution (SR) techniques. Compared with SR rec…
Cross-modal Contrastive Distillation for Instructional Activity Anticipation
Zhengyuan Yang, Jingen Liu, Jing Huang +4
In this study, we aim to predict the plausible future action steps given an observation of the past and study the task of instructional activity anticipation. Unlike previous antic…