paper-with-me

홈 › Papers

Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships

2022-03-27 · CVPR 2022 1 · Chao Lou, Wenjuan Han, Yuhuan Lin, Zilong Zheng

Understanding realistic visual scene images together with language descriptions is a fundamental task towards generic visual understanding. Previous works have shown compelling comprehensive results by building hierarchical structures for visual scenes (e.g., scene graphs) and natural languages (e.g., dependency trees), individually. However, how to construct a joint vision-language (VL) structure has barely been investigated. More challenging but worthwhile, we introduce a new task that targets on inducing such a joint VL structure in an unsupervised manner. Our goal is to bridge the visual scene graphs and linguistic dependency trees seamlessly. Due to the lack of VL structural data, we start by building a new dataset VLParse. Rather than using labor-intensive labeling from scratch, we propose an automatic alignment procedure to produce coarse structures followed by human refinement to produce high-quality ones. Moreover, we benchmark our dataset by proposing a contrastive learning (CL)-based framework VLGAE, short for Vision-Language Graph Autoencoder. Our model obtains superior performance on two derived tasks, i.e., language grammar induction and VL phrase grounding. Ablations show the effectiveness of both visual cues and dependency relationships on fine-grained VL structure construction.

📄 PDF Abstract BibTeX arXiv:2203.14260

Code (1)

bigai-research/vlgae 공식 구현 pytorch

Tasks

Contrastive LearningPhrase Grounding

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation

2021-01-27 · EACL 2021 2 · Kemal Kurniawan, Lea Frermann, Philip Schulz, Trevor Cohn

Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple `direct transfer' of a learned model based on a multilingual input encoding has provided a s…

ARCCross-Lingual Transfer

On the Role of Supervision in Unsupervised Constituency Parsing

2020-10-06 · EMNLP 2020 11 · Haoyue Shi, Karen Livescu, Kevin Gimpel

We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing $F_1$ score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baseline…

Constituency ParsingData AugmentationModel Selection

Unsupervised and Few-shot Parsing from Pretrained Language Models

2022-06-10 · Zhiyuan Zeng, Deyi Xiong

Pretrained language models are generally acknowledged to be able to encode syntax [Tenney et al., 2019, Jawahar et al., 2019, Hewitt and Manning, 2019]. In this article, we propose UPOA, an Unsupervised constituent Parsi…

Language Modelling

Applying Unsupervised Semantic Segmentation to High-Resolution UAV Imagery for Enhanced Road Scene Parsing

2024-02-05 · Zihan Ma, Yongshang Li, Ronggui Ma, Chen Liang

There are two challenges presented in parsing road scenes from UAV images: the complexity of processing high-resolution images and the dependency on extensive manual annotations required by traditional supervised deep le…

Language ModellingRepresentation LearningScene ParsingSelf-Supervised Learning+2

UBoCo : Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection

2021-11-29 · Hyolim Kang, Jinwoo Kim, Taehyun Kim, Seon Joo Kim

Generic Event Boundary Detection (GEBD) is a newly suggested video understanding task that aims to find one level deeper semantic boundaries of events. Bridging the gap between natural human perception and video understa…

Boundary DetectionContrastive LearningGeneric Event Boundary Detectionvalid+1