activity
20192026
most citedBackbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification

5 citations · 8 across the 4 of their papers we have counts for

collaborators
Showing 2021Show all

1 paper · 1 filter

cs.CV2021

Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels

Seulki Park, Hwanjun Song, Daeho Um +3

Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a…