yekeren / Cap2Det

Implementation of our ICCV 2019 paper "Cap2Det: Learning to AmplifyWeak Caption Supervision for Object Detection"
Apache License 2.0
29 stars 9 forks source link

Describe our benchmark #9

Closed yekeren closed 4 years ago

yekeren commented 5 years ago

The rough idea is that (A standard):

Researchers are allowed to use any type of textual prediction models. However, the training set of the detector is limited to MIRFlickr1M. They can use methods to mine a subset of paired UGC tag and image data from MIRFlickr1M (e.g., we form our Flickr200K training set). Finally, all studies report mAP@.5 on the VOC07 test set.