Rectifying the Data Bias in Knowledge Distillation
Open paper
Benchmark
Model
Rank
Results
face-verification-on-ijb-c
L2E+IS-sampling
–
TAR @ FAR=1e-5: 93.25%
TAR @ FAR=1e-4: 95.49%
TAR @ FAR=1e-3: 97.05%
…
Rank counts only results with a code link.