Fengshuo Zhang — accepted AI-conference papers

2024

Multiscale Attention Distillation for Object Detection

ICASSP 2024accepted

Object detection is a critical task in computer vision that involves identifying and localizing objects in images. Deep learning-based object detectors have achieved impressive performance, but their computational requirements limit their deployment in resource-constrained scenarios. Knowledge disti…

Cited by 0 Source ↗Scholar ↗

2023

A Multi-modal Debiasing Model with Dynamical Constraint for Robust Visual Question Answering

Yu Li, Bojie Hu, Fengshuo Zhang, Yahan Yu, Jian Liu, Yufeng Chen +1

ACL 2023findings

Recent studies have pointed out that many well-developed Visual Question Answering (VQA) systems suffer from bias problem. Despite the remarkable performance gained on In-Distribution (ID) datasets, the VQA model might merely capture the superficial correlation from question to answer rather than sh…

Cited by 10 Source ↗PDF ↗Scholar ↗