Detecting Twenty-thousand Classes using Image-level Supervision

Detic: A Detector with image classes that can use image-level labels to easily train detectors.

Detecting Twenty-thousand Classes using Image-level Supervision,
Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra,
ECCV 2022 (arXiv 2201.02605)

Features

• Detects any class given class names (using CLIP).

• We train the detector on ImageNet-21K dataset with 21K classes.

• Cross-dataset generalization to OpenImages and Objects365 without finetuning.

• State-of-the-art results on Open-vocabulary LVIS and Open-vocabulary COCO.

Detic_C2_SwinB_896_4x Performance

Standard LVIS

Note

• All Detic models use the overlap classes between ImageNet-21K and LVIS as image-labeled data;

• The models with C2 are trained using our improved LVIS baseline in the paper, including CenterNet2 detector, Federated loss, large-scale jittering, etc.