Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection
원문 초록
Open-vocabulary object detection (OVOD) has recently gained significant attention as a crucial step toward achieving human-like visual intelligence. Existing OVOD methods extend target vocabulary from pre-defined categories to open-world by transferring knowledge of arbitrary concepts from vision-language pre-training models to the detectors. While previous methods have shown remarkable successes, they suffer from indirect supervision or limited transferable concepts. In this paper, we propose a simple yet effective method to directly learn region-text alignment for arbitrary concepts. Specifically, the proposed method aims to learn arbitrary image-to-text mapping for pseudo-labeling of arbitrary concepts, named Pseudo-Labeling for Arbitrary Concepts (PLAC). The proposed method shows competitive performance on the standard OVOD benchmark for noun concepts and a large improvement on referring expression comprehension benchmark for arbitrary concepts.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
FG-CLIP: Fine-Grained Visual and Textual Alignment
ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction
Gen-n-Val: Agentic Image Data Generation and Validation
Improving Medical Visual Representation Learning with Pathological-level Cross-Modal Alignment and Correlation Exploration
From Data to Modeling: Fully Open-vocabulary Scene Graph Generation
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.