paper-with-me

홈 › Papers

Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset

2021-07-09 · ACL (WOAH) 2021 8 · Hannah Rose Kirk, Yennie Jun, Paulius Rauba, Gal Wachtel, Ruining Li, Xingjian Bai, Noah Broestl, Martin Doff-Sotta, Aleksandar Shtedritski, Yuki M. Asano

Hateful memes pose a unique challenge for current machine learning systems because their message is derived from both text- and visual-modalities. To this effect, Facebook released the Hateful Memes Challenge, a dataset of memes with pre-extracted text captions, but it is unclear whether these synthetic examples generalize to memes in the wild'. In this paper, we collect hateful and non-hateful memes from Pinterest to evaluate out-of-sample performance on models pre-trained on the Facebook dataset. We find that memes in the wild differ in two key aspects: 1) Captions must be extracted via OCR, injecting noise and diminishing performance of multimodal models, and 2) Memes are more diverse than traditional memes', including screenshots of conversations or text on a plain background. This paper thus serves as a reality check for the current benchmark of hateful meme detection and its applicability for detecting real world hate.

📄 PDF Abstract BibTeX arXiv:2107.04313

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

Feels Bad Man: Dissecting Automated Hateful Meme Detection Through the Lens of Facebook's Challenge

2022-02-17 · Catherine Jennifer, Fatemeh Tahmasbi, Jeremy Blackburn, Gianluca Stringhini 외

Internet memes have become a dominant method of communication; at the same time, however, they are also increasingly being used to advocate extremism and foster derogatory beliefs. Nonetheless, we do not have a firm unde…

Multimodal Learning for Hateful Memes Detection

2020-11-25 · Yi Zhou, Zhenhao Chen

Memes are used for spreading ideas through social networks. Although most memes are created for humor, some memes become hateful under the combination of pictures and text. Automatically detecting the hateful memes can h…

Image CaptioningMultimodal Deep Learning

On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning

2022-12-13 · Yiting Qu, Xinlei He, Shannon Pierson, Michael Backes 외

The dissemination of hateful memes online has adverse effects on social media platforms and the real world. Detecting hateful memes is challenging, one of the reasons being the evolutionary nature of memes; new hateful m…

Contrastive Learning

Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning

2023-11-14 · Jingbiao Mei, Jinghong Chen, Weizhe Lin, Bill Byrne 외

Hateful memes have emerged as a significant concern on the Internet. Detecting hateful memes requires the system to jointly understand the visual and textual modalities. Our investigation reveals that the embedding space…

Contrastive LearningHateful Meme ClassificationMeme ClassificationRetrieval

Findings of the WOAH 5 Shared Task on Fine Grained Hateful Memes Detection

2021-08-01 · ACL (WOAH) 2021 8 · Lambert Mathias, Shaoliang Nie, Aida Mostafazadeh Davani, Douwe Kiela 외

We present the results and main findings of the shared task at WOAH 5 on hateful memes detection. The task include two subtasks relating to distinct challenges in the fine-grained detection of hateful memes: (1) the prot…