Search Results for author: Jiaying Zhu

Found 8 papers, 6 papers with code

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

DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS Camera

1 code implementation12 Jun 2024 Senyan Xu, Zhijing Sun, Jiaying Zhu, Yurui Zhu, Xueyang Fu, Zheng-Jun Zha

Coarse demosaicing network is designed to produce a preliminary high-quality estimate of the RGB image from the HybridEVS raw data while the pixel correction network enhances the performance of image restoration and mitigates the impact of defective pixels.

Data Augmentation Demosaicking +1

Quantifying Emergence in Large Language Models

1 code implementation21 May 2024 Hang Chen, Xinyu Yang, Jiaying Zhu, Wenya Wang

Empirical results show that (1) our method gives consistent measurements which align with existing observations based on performance metrics, validating the effectiveness of our emergence quantification; (2) our proposed metric uncovers novel emergence patterns such as the correlations between the variance of our metric and the number of ``shots'' in ICL, which further suggests a new way of interpreting hallucinations in LLMs; (3) we offer a potential solution towards estimating the emergence of larger and closed-resource LMs via smaller LMs like GPT-2.

In-Context Learning

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

no code implementations17 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 implementation29 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

Cannot find the paper you are looking for? You can Submit a new open access paper.