HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Meme Classification On Hateful Memes

평가 지표

Accuracy
ROC-AUC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Accuracy
ROC-AUC
Paper TitleRepository
LMM-RGCL (Qwen2-VL-7B)0.8210.911Improved Fine-Tuning of Large Multimodal Models for Hateful Meme Detection
Flamingo (few-shot:32)-0.700Flamingo: a Visual Language Model for Few-Shot Learning
Vilio0.6950.825Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes
CLIP (zero-shot)-0.661Learning Transferable Visual Models From Natural Language Supervision
Human0.8470.8265The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
SEER (RegNet10B)-0.734Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
Ron Zhu0.7320.845Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution
Pro-Cap0.7230.809Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection
PaLI-X-VPD-0.892Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models-
Visual BERT COCO0.6950.754The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
Flamingo (fine-tuned)-0.866Flamingo: a Visual Language Model for Few-Shot Learning
ISSUES-0.855Mapping Memes to Words for Multimodal Hateful Meme Classification
HateDetectron270.7650.811Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge-
RGCL (CLIP)0.7880.870Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning
Hate-CLIPper - Align-0.858Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features
LMM-RGCL (LLaVA-1.5-7B)0.8090.897Improved Fine-Tuning of Large Multimodal Models for Hateful Meme Detection
LMM-RGCL (Qwen2-VL-2B)0.7910.884Improved Fine-Tuning of Large Multimodal Models for Hateful Meme Detection
0 of 17 row(s) selected.