Efficient Action Recognition Using Confidence Distillation. (arXiv:2109.02137v2 [cs.CV] UPDATED)

Modern neural networks are powerful predictive models. However, when it comes
to recognizing that they may be wrong about their predictions, they perform
poorly. For example, for one of the most common activation functions, the ReLU
and its variants, even a well-calibrated model can produce incorrect but high
confidence predictions. In the related task of action recognition, most current
classification methods are based on clip-level classifiers that densely sample
a given video for non-overlapping, same-sized clips and aggregate the results …

arxiv confidence cv distillation