arXiv:2309.12110
Exploiting CLIP-based Multi-modal Approach for Artwork Classification and Retrieval
원문 초록
Given the recent advances in multimodal image pretraining where visual models trained with semantically dense textual supervision tend to have better generalization capabilities than those trained using categorical attributes or through unsupervised techniques, in this work we investigate how recent CLIP model can be applied in several tasks in artwork domain. We perform exhaustive experiments on the NoisyArt dataset which is a dataset of artwork images crawled from public resources on the web. On such dataset CLIP achieves impressive results on (zero-shot) classification and promising results in both artwork-to-artwork and description-to-artwork domain.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models
Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models
Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening Mammography
Harmonizing and Merging Source Models for CLIP-based Domain Generalization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.