paper-with-me

홈 › Papers

IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretraining

2023-03-06 · Chihaya Matsuhira, Marc A. Kastner, Takahiro Komamizu, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide

Recently, large-scale Vision and Language (V\&L) pretraining has become the standard backbone of many multimedia systems. While it has shown remarkable performance even in unseen situations, it often performs in ways not intuitive to humans. Particularly, they usually do not consider the pronunciation of the input, which humans would utilize to understand language, especially when it comes to unknown words. Thus, this paper inserts phonetic prior into Contrastive Language-Image Pretraining (CLIP), one of the V\&L pretrained models, to make it consider the pronunciation similarity among its pronunciation inputs. To achieve this, we first propose a phoneme embedding that utilizes the phoneme relationships provided by the International Phonetic Alphabet (IPA) chart as a phonetic prior. Next, by distilling the frozen CLIP text encoder, we train a pronunciation encoder employing the IPA-based embedding. The proposed model named IPA-CLIP comprises this pronunciation encoder and the original CLIP encoders (image and text). Quantitative evaluation reveals that the phoneme distribution on the embedding space represents phonetic relationships more accurately when using the proposed phoneme embedding. Furthermore, in some multimodal retrieval tasks, we confirm that the proposed pronunciation encoder enhances the performance of the text encoder and that the pronunciation encoder handles nonsense words in a more phonetic manner than the text encoder. Finally, qualitative evaluation verifies the correlation between the pronunciation encoder and human perception regarding pronunciation similarity.

📄 PDF Abstract BibTeX arXiv:2303.03144

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio

2026-06-10 · Hao Zhang, Qinran Lin, Linqi Song, Yong Li arxiv

Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In …

Object Detection

PhenoLIP: Integrating Phenotype Ontology Knowledge into Medical Vision-Language Pretraining

2026-02-05 · Cheng Liang, Chaoyi Wu, Weike Zhao, Ya Zhang 외 arxiv

Recent progress in large-scale CLIP-like vision-language models(VLMs) has greatly advanced medical image analysis. However, most existing medical VLMs still rely on coarse image-text contrastive objectives and fail to ca…

Phenotype classificationKnowledge DistillationCross-Modal Retrieval

CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation

2023-12-19 · Monika Wysoczańska, Oriane Siméoni, Michaël Ramamonjisoa, Andrei Bursuc 외

The popular CLIP model displays impressive zero-shot capabilities thanks to its seamless interaction with arbitrary text prompts. However, its lack of spatial awareness makes it unsuitable for dense computer vision tasks…

Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSemantic Segmentation

SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces

2023-07-23 · Ivan Vallés-Pérez, Grzegorz Beringer, Piotr Bilinski, Gary Cook 외

Numerous examples in the literature proved that deep learning models have the ability to work well with multimodal data. Recently, CLIP has enabled deep learning systems to learn shared latent spaces between images and t…

PET Image Denoising via Text-Guided Diffusion: Integrating Anatomical Priors through Text Prompts

2025-02-28 · Boxiao Yu, Savas Ozdemir, Jiong Wu, Yizhou Chen 외

Low-dose Positron Emission Tomography (PET) imaging presents a significant challenge due to increased noise and reduced image quality, which can compromise its diagnostic accuracy and clinical utility. Denoising diffusio…

DenoisingDiagnosticImage Denoising