O

Omdet Turbo Swin Tiny Hf

Developed by omlab
OmDet-Turbo is an efficient fusion-head open-vocabulary detection model based on real-time Transformer, suitable for zero-shot object detection tasks.
Downloads 36.29k
Release Time : 9/24/2024

Model Overview

Proposed by Om AI Lab, this model adopts the Swin Transformer architecture, supports open-vocabulary object detection, and can detect object categories not seen in the training data.

Model Features

Open-vocabulary Detection
Supports detecting object categories not present in the training data, requiring only the category names for detection.
Efficient Fusion Head
Incorporates an innovative fusion head design, enhancing detection efficiency and accuracy.
Batch Multi-image Inference
Supports detection with different text prompts and categories for different images in the same batch.

Model Capabilities

Zero-shot Object Detection
Open-vocabulary Recognition
Multi-category Simultaneous Detection
Batch Image Processing

Use Cases

Intelligent Surveillance
Anomalous Object Detection
Detects specific or anomalous objects in surveillance scenarios.
Accurately identifies object categories not pre-trained.
Retail Analytics
Product Recognition
Identifies new or unlabeled products on shelves.
Detects newly launched products without retraining.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase