Papers with Code 아카이브
Open Vocabulary Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 4
- 보존된 평가 기록
- 64
Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the training phase. The goal is to detect novel classes defined by an unbounded (open) vocabulary at inference.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Generating Enhanced Negatives for Training Language-Based Object Detectors
GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection
Weakly Supervised Open-Vocabulary Object Detection
CLIM: Contrastive Language-Image Mosaic for Region Representation
Simple Image-level Classification Improves Open-vocabulary Object Detection
ProxyDet: Synthesizing Proxy Novel Classes via Classwise Mixup for Open-Vocabulary Object Detection
Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection
The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning
Enhancing Novel Object Detection via Cooperative Foundational Models
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention
Meta-Adapter: An Online Few-shot Learner for Vision-Language Model
YOLOv8-Based Visual Detection of Road Hazards: Potholes, Sewer Covers, and Manholes
Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
LP-OVOD: Open-Vocabulary Object Detection by Linear Probing
CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
OV-VG: A Benchmark for Open-Vocabulary Visual Grounding
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Region-centric Image-Language Pretraining for Open-Vocabulary Detection
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Detect Everything with Few Examples
EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment
Contrastive Feature Masking Open-Vocabulary Vision Transformer
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation
Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection
Taming Self-Training for Open-Vocabulary Object Detection
Described Object Detection: Liberating Object Detection with Flexible Expressions
Open-Vocabulary Object Detection via Scene Graph Discovery
Scaling Open-Vocabulary Object Detection
Multi-Modal Classifiers for Open-Vocabulary Object Detection
LOWA: Localize Objects in the Wild with Attributes
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.