HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes
원문 초록
Amidst the rise of Large Multimodal Models (LMMs) and their widespread application in generating and interpreting complex content, the risk of propagating biased and harmful memes remains significant. Current safety measures often fail to detect subtly integrated hateful content within ``Confounder Memes''. To address this, we introduce \textsc{HateSieve}, a new framework designed to enhance the detection and segmentation of hateful elements in memes. \textsc{HateSieve} features a novel Contrastive Meme Generator that creates semantically paired memes, a customized triplet dataset for contrastive learning, and an Image-Text Alignment module that produces context-aware embeddings for accurate meme segmentation. Empirical experiments on the Hateful Meme Dataset show that \textsc{HateSieve} not only surpasses existing LMMs in performance with fewer trainable parameters but also offers a robust mechanism for precisely identifying and isolating hateful content. \textcolor{red}{Caution: Contains academic discussions of hate speech; viewer discretion advised.}
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Quantum-Informed Contrastive Learning with Dynamic Mixup Augmentation for Class-Imbalanced Expert Systems
Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories
An Interpretable Representation Learning Approach for Diffusion Tensor Imaging
Adversarial Modality Alignment Network for Cross-Modal Molecule Retrieval
Attributes Shape the Embedding Space of Face Recognition Models
RadiomicsRetrieval: A Customizable Framework for Medical Image Retrieval Using Radiomics Features
토론
이 논문과 연결된 포럼 글이 아직 없습니다.