SRCB at SemEval-2022 Task 5: Pretraining Based Image to Text Late Sequential Fusion System for Multimodal Misogynous Meme Identification

Jing Zhang, Yujin Wang

Abstract
Online misogyny meme detection is an image/text multimodal classification task, the complicated relation of image and text challenges the intelligent system’s modality fusion learning capability. In this paper, we investigate the single-stream UNITER and dual-stream CLIP multimodal pretrained models on their capability to handle strong and weakly correlated image/text pairs. The XGBoost classifier with image features extracted by the CLIP model has the highest performance and being robust on domain shift. Based on this, we propose the PBR system, an ensemble system of Pretraining models, Boosting method and Rule-based adjustment, text information is fused into the system using our late sequential fusion scheme. Our system ranks 1st place on both sub-task A and sub-task B of the SemEval-2022 Task 5 Multimedia Automatic Misogyny Identification, with 0.834/0.731 macro F1 scores for sub-task A/B correspondingly.
Anthology ID:
2022.semeval-1.81
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Guy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
585–596
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2022.semeval-1.81/
DOI:
10.18653/v1/2022.semeval-1.81
Bibkey:
Cite (ACL):
Jing Zhang and Yujin Wang. 2022. SRCB at SemEval-2022 Task 5: Pretraining Based Image to Text Late Sequential Fusion System for Multimodal Misogynous Meme Identification. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 585–596, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
SRCB at SemEval-2022 Task 5: Pretraining Based Image to Text Late Sequential Fusion System for Multimodal Misogynous Meme Identification (Zhang & Wang, SemEval 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2022.semeval-1.81.pdf
PDF Search Fix metadata