Demo code available at: https://github.com/jhoffman/lsda This code accompanies the arXiv report.
- Includes all leaf synsets + 200 detection categories
- Pre-trained Detection Model
- Caffe Weights for 200 strong detectors
- Caffe Weights for 7K weak detectors
To try out an example, run:
startup;
detect10k_demo(rcnn_model, rcnn_feat, 'ex_img.jpg');
This code requires Caffe to be installed. For Installation instructions visit: http://caffe.berkeleyvision.org
"LSDA: Large Scale Detection Through Adaptation." J. Hoffman,
S. Guadarrama, E. Tzeng, R. Hu, J. Donahue, R. Girshick, T. Darrell, and
K. Saenko. Neural Information Processing Systems (NIPS), 2014.