paper-with-me

Papers

Deconfounded Image Captioning: A Causal Retrospect

2020-03-09 · Xu Yang, Hanwang Zhang, Jianfei Cai

Dataset bias in vision-language tasks is becoming one of the main problems which hinders the progress of our community. Existing solutions lack a principled analysis about why modern image captioners easily collapse into dataset bias. In this paper, we present a novel perspective: Deconfounded Image Captioning (DIC), to find out the answer of this question, then retrospect modern neural image captioners, and finally propose a DIC framework: DICv1.0 to alleviate the negative effects brought by dataset bias. DIC is based on causal inference, whose two principles: the backdoor and front-door adjustments, help us review previous studies and design new effective models. In particular, we showcase that DICv1.0 can strengthen two prevailing captioning models and can achieve a single-model 131.1 CIDEr-D and 128.4 c40 CIDEr-D on Karpathy split and online split of the challenging MS COCO dataset, respectively. Interestingly, DICv1.0 is a natural derivation from our causal retrospect, which opens promising directions for image captioning.

📄 PDF Abstract BibTeX arXiv:2003.03923

Code (0)

등록된 구현이 없습니다.

Tasks

Causal InferenceImage Captioning

Similar Papers 제목 키워드 기반

Causal Inference With Selectively Deconfounded Data

2020-02-25 · Kyra Gan, Andrew A. Li, Zachary C. Lipton, Sridhar Tayur

Given only data generated by a standard confounding graph with unobserved confounder, the Average Treatment Effect (ATE) is not identifiable. To estimate the ATE, a practitioner must then either (a) collect deconfounded …

Causal Inference

Deconfounded Visual Grounding

2021-12-31 · Jianqiang Huang, Yu Qin, Jiaxin Qi, Qianru Sun 외

We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivi…

Referring ExpressionVisual GroundingVisual Reasoning

Deconfounded Reasoning for Multimodal Fake News Detection via Causal Intervention

2025-04-12 · Moyang Liu, Kaiying Yan, Yukun Liu, Ruibo Fu 외

The rapid growth of social media has led to the widespread dissemination of fake news across multiple content forms, including text, images, audio, and video. Traditional unimodal detection methods fall short in addressi…

DisentanglementFake News Detection

Towards Deconfounded Image-Text Matching with Causal Inference

2024-08-22 · Wenhui Li, Xinqi Su, Dan Song, Lanjun Wang 외

Prior image-text matching methods have shown remarkable performance on many benchmark datasets, but most of them overlook the bias in the dataset, which exists in intra-modal and inter-modal, and tend to learn the spurio…

Causal InferenceImage-text matchingText Matching

The Deconfounded Recommender: A Causal Inference Approach to Recommendation

2018-08-20 · Yixin Wang, Dawen Liang, Laurent Charlin, David M. Blei

The goal of recommendation is to show users items that they will like. Though usually framed as a prediction, the spirit of recommendation is to answer an interventional question---for each user and movie, what would the…

Causal InferenceRecommendation Systems