paper-with-me

Papers

Hyperbolic Image-Text Representations

2023-04-18 · Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, Ramakrishna Vedantam

Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP do not explicitly capture such hierarchy. We propose MERU, a contrastive model that yields hyperbolic representations of images and text. Hyperbolic spaces have suitable geometric properties to embed tree-like data, so MERU can better capture the underlying hierarchy in image-text datasets. Our results show that MERU learns a highly interpretable and structured representation space while being competitive with CLIP's performance on standard multi-modal tasks like image classification and image-text retrieval. Our code and models are available at https://www.github.com/facebookresearch/meru

📄 PDF Abstract BibTeX arXiv:2304.09172

Code (2)

facebookresearch/meru 공식 구현 pytorch
naver-ai/hype pytorch

Tasks

image-classificationImage ClassificationImage-text RetrievalRetrievalText 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

HYDEN: Hyperbolic Density Representations for Medical Images and Reports

2024-08-19 · Zhi Qiao, Linbin Han, XianTong Zhen, Jia-Hong Gao 외

In light of the inherent entailment relations between images and text, hyperbolic point vector embeddings, leveraging the hierarchical modeling advantages of hyperbolic space, have been utilized for visual semantic repre…

Representation Learning

Accept the Modality Gap: An Exploration in the Hyperbolic Space

2024-01-01 · CVPR 2024 1 · Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Ajanthan Thalaiyasingam

Recent advancements in machine learning have spotlighted the potential of hyperbolic spaces as they effectively learn hierarchical feature representations. While there has been progress in leveraging hyperbolic space…

Image to textImage-to-Text RetrievalRetrievalText Retrieval

HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval

2024-01-14 · Zexuan Qiu, Jiahong Liu, Yankai Chen, Irwin King

Existing unsupervised deep product quantization methods primarily aim for the increased similarity between different views of the identical image, whereas the delicate multi-level semantic similarities preserved between …

Contrastive LearningImage RetrievalQuantizationRetrieval+2

ARGENT: Adaptive Hierarchical Image-Text Representations

2026-03-24 · Chuong Huynh, Hossein Souri, Abhinav Kumar, Vitali Petsiuk 외 arxiv

Large-scale Vision-Language Models (VLMs) such as CLIP learn powerful semantic representations but operate in Euclidean space, which fails to capture the inherent hierarchical structure of visual and linguistic concepts.…

Image ClassificationImage Retrieval

HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation

2024-03-01 · CVPR 2024 1 · Zhiying Leng, Tolga Birdal, Xiaohui Liang, Federico Tombari

3D shape generation from text is a fundamental task in 3D representation learning. The text-shape pairs exhibit a hierarchical structure, where a general text like ``chair" covers all 3D shapes of the chair, while more d…

3D Shape GenerationRepresentation LearningText-to-Shape Generation