Open Vocabulary Object Detection
4개 벤치마크 · 논문 147편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
Open-Vocabulary DETR with Conditional Matching
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
YOLO-World: Real-Time Open-Vocabulary Object Detection
Scaling Open-Vocabulary Object Detection
Papers
Unveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs
Open-vocabulary object detection seeks to identify novel object categories that were not part of the training data. Many knowledge distillation-based approaches have shown promising performance by transferring knowledge …
Open Vocabulary Object DetectionKnowledge DistillationGeneral and Efficient Visual Goal-Conditioned Reinforcement Learning using Object-Agnostic Masks
Goal-conditioned reinforcement learning (GCRL) allows agents to learn diverse objectives using a unified policy. The success of GCRL, however, is contingent on the choice of goal representation. In this work, we propose …
Open Vocabulary Object DetectionReinforcement LearningATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction
Vision-language models such as CLIP have recently propelled open-vocabulary dense prediction tasks by enabling recognition of a broad range of visual concepts. However, CLIP still struggles with fine-grained, region-leve…
object-detectionObject DetectionOpen-vocabulary object detectionOpen Vocabulary Object Detection+1Gen-n-Val: Agentic Image Data Generation and Validation
Recently, Large Language Models (LLMs) and Vision Large Language Models (VLLMs) have demonstrated impressive performance as agents across various tasks while data scarcity and label noise remain significant challenges in…
Image HarmonizationInstance SegmentationObjectobject-detection+6From Data to Modeling: Fully Open-vocabulary Scene Graph Generation
We present OvSGTR, a novel transformer-based framework for fully open-vocabulary scene graph generation that overcomes the limitations of traditional closed-set models. Conventional methods restrict both object and relat…
Graph GenerationKnowledge DistillationNovel ConceptsOpen-vocabulary object detection+3FG-CLIP: Fine-Grained Visual and Textual Alignment
Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short c…
Image-text Retrievalobject-detectionObject DetectionOpen-vocabulary object detection+5