LVIS

Progress on object detection is enabled by datasets that focus the research community's attention on open challenges. This process led us from simple images to complex scenes and from bounding boxes to segmentation masks. In this work, we introduce LVIS (pronounced `el-vis'): a new dataset for Large Vocabulary Instance

Papers using LVIS (5)

VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio2026Moondream Segmentation: From Words to Masks2026QATMA: Quantization-Aware Training with Multimodal Alignment for Open-Vocabulary Object Detection2026DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection2026Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment2026