Papers with Code 아카이브
Open Vocabulary Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 10
Given an image and nothing else, i.e. no prompts or candidate labels, the task is to generate an accurate textual fine-grained classification label from the entire pool of simple and compound nouns in the English language.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion
FusionBench: A Comprehensive Benchmark of Deep Model Fusion
Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
Continual Learning in Open-vocabulary Classification with Complementary Memory Systems
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.