issues
search
long8v
/
PTIR
Paper Today I Read
19
stars
0
forks
source link
[92] Long-Tail Learning via Logit Adjustment
#101
Open
long8v
opened
1 year ago
long8v
commented
1 year ago
paper
,
code
TL;DR
I read this because.. :
#57 에서 사용한 trick
task :
long-tail image classification
problem :
real-world에서는 class가 imbalance한 경우가 많다
idea :
label frequency 기반으로 logit adjustment를 함
architecture :
ResNet-32, ResNet-50
objective :
softmax의 exponential에 들어가는 값에다가 class별 frequency를 $\tau$를 곱해서 더함.
baseline :
ERM, weight normalisation, Adaptive, Equalized
data :
CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, iNaturalist2018
evaluation :
balanced error(class별 평균)
result :
outperform baselines
limitation / things I cannot understand :
수식 및 논리를 이해하지는 않고 읽음
Details
Post-hoc logit adjustment
Logit adjusted softmax cross-entropy
Result
paper, code
TL;DR
Details
Post-hoc logit adjustment
Logit adjusted softmax cross-entropy
Result