| 2 outputa | +2 gradb | +5 gradc | +2 grad + loss + labeld | +3 grad + loss + labele |
---|
lossInstance | 0.7 | 0.61 | 0.61 | 0.57 | 0.57 |
lossPerson | 0.7 | 0.61 | 0.62 | 0.59 | 0.58 |
- For reference, the baseline (binary cross-entropy of random guesses for a balanced data) would be \(- \log(1/2) = 0.693\).
- aTakes the two last outputs (the target model output and the layer just before it) of the target model as the input
- bTakes the two last outputs and also the two gradients before the last gradient of the target model
- cTakes all the “+2 grad” and also the last gradient of three different sections of the target model (boundary, face, eyes)
- dTakes the two last layers outputs and also the two before the last gradient and label and loss of target model
- eTakes the two last layers outputs and also the three last gradients and label and loss of target model