Generating Visual Representations for Zero-Shot Classification
원문 초록
This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to as the Zero-Shot classification task (ZSC). Most of the previous methods rely on learning a common embedding space allowing to compare visual features of unknown categories with semantic descriptions. This paper argues that these approaches are limited as i) efficient discrimi-native classifiers can't be used ii) classification tasks with seen and unseen categories (Generalized Zero-Shot Classification or GZSC) can't be addressed efficiently. In contrast , this paper suggests to address ZSC and GZSC by i) learning a conditional generator using seen classes ii) generate artificial training examples for the categories without exemplars. ZSC is then turned into a standard supervised learning problem. Experiments with 4 generative models and 5 datasets experimentally validate the approach, giving state-of-the-art results on both ZSC and GZSC.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
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
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models
AmorLIP: Efficient Language-Image Pretraining via Amortization
Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption
토론
이 논문과 연결된 포럼 글이 아직 없습니다.