detic

We have hosted the application detic in order to run this application in our online workstations with Wine or directly.

Quick description about detic:

Detic (�Detecting Twenty-thousand Classes using Image-level Supervision�) is a large-vocabulary object detector that scales beyond fully annotated datasets by leveraging image-level labels. It decouples localization from classification, training a strong box localizer on standard detection data while learning classifiers from weak supervision and large image-tag corpora. A shared region proposal backbone feeds a flexible classification head that can expand to tens of thousands of categories without exhaustive box annotations. The system supports zero- or few-shot extension to novel categories via semantic embeddings and class name supervision, making �open-world� detection practical. Built on Detectron2, the repo includes configs, pretrained weights, and conversion tools to mix fully and weakly supervised sources. Detic is especially useful for applications where label space is vast and long-tailed, but dense bounding-box annotation is infeasible.

Features:

• Large-vocabulary detection with decoupled localization and classification
• Training from image-level tags to expand categories at scale
• Compatibility with Detectron2 backbones and region proposal heads
• Zero-/few-shot transfer via semantic class embeddings and names
• Configs and weights for mixing fully and weakly supervised data
• Tools for dataset conversion, evaluation, and large-label-space deployments

Programming Language: Python.
Categories: