Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering

1 code implementation • EMNLP 2020 • Zujie Liang, Weitao Jiang, Haifeng Hu, Jiaying Zhu

In the task of Visual Question Answering (VQA), most state-of-the-art models tend to learn spurious correlations in the training set and achieve poor performance in out-of-distribution test data.

Contrastive Learning counterfactual +2

A Study on the Performance of Generative Pre-trained Transformer (GPT) in Simulating Depressed Individuals on the Standardized Depressive Symptom Scale

no code implementations • 17 Jul 2023 • Sijin Cai, Nanfeng Zhang, Jiaying Zhu, Yanjie Liu, Yongjin Zhou

Compare GPT's responses with expected results, assess its understanding of depressive symptoms, and performance differences under different conditions.

Edge-Aware Regional Message Passing Controller for Image Forgery Localization

no code implementations • CVPR 2023 • Dong Li, Jiaying Zhu, Menglu Wang, Jiawei Liu, Xueyang Fu, Zheng-Jun Zha

In the second step, guided by the learnable edges, a region message passing controller is devised to weaken the message passing between the forged and authentic regions.

Binarization graph construction

LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering

1 code implementation • 29 May 2021 • Zujie Liang, Haifeng Hu, Jiaying Zhu

Most existing Visual Question Answering (VQA) systems tend to overly rely on language bias and hence fail to reason from the visual clue.

Question Answering Visual Question Answering