Class hierarchy

Object detection

Transfer of learning

Knowledge transfer

Economics

Set (abstract data type)

Market economy

Parallel computing

Computer science

Minimum bounding box

Transfer (computing)

Hierarchy

Supervised learning

Psychology

Pattern recognition (psychology)

Image (mathematics)

Object (grammar)

Object-oriented programming

Psychotherapist

Generality

Artificial intelligence

Programming language

Knowledge management

Bounding overwatch

Artificial neural network

Training set

Class (philosophy)

Machine learning

We propose to revisit knowledge transfer for training object detectors on target classes from weakly supervised training images, helped by a set of source classes with bounding-box annotations. We present a unified knowledge transfer framework based on training a single neural network multi-class object detector over all source classes, organized in a semantic hierarchy. This generates proposals with scores at multiple levels in the hierarchy, which we use to explore knowledge transfer over a broad range of generality, ranging from class-specific (bycicle to motorbike) to class-generic (objectness to any class). Experiments on the 200 object classes in the ILSVRC 2013 detection dataset show that our technique (1) leads to much better performance on the target classes (70.3% CorLoc, 36.9% mAP) than a weakly supervised baseline which uses manually engineered objectness [11] (50.5% CorLoc, 25.4% mAP). (2) delivers target object detectors reaching 80% of the mAP of their fully supervised counterparts. (3) outperforms the best reported transfer learning results on this dataset (+41% CorLoc and +3% mAP over [18, 46], +16.2% mAP over [32]). Moreover, we also carry out several across-dataset knowledge transfer experiments [27, 24, 35] and find that (4) our technique outperforms the weakly supervised baseline in all dataset pairs by 1.5 Ã- - 1.9Ã-, establishing its general applicability.

Revisiting Knowledge Transfer for Training Object Class Detectors