This shows you the differences between two versions of the page.
— |
papers:balestriero-2022 [2023/08/29 06:08] (current) leonb created |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ===== The Effects of Regularization and Data Augmentation are Class Dependent ===== | ||
+ | {{ randalls.png? | ||
+ | |||
+ | // | ||
+ | performances by constraining a model’s complexity. Current Deep Networks heavily rely on regularizers such as Data-Augmentation (DA) or weight-decay, | ||
+ | i.e. cross-validation, | ||
+ | is unfair across classes. The optimal amount of DA or weight decay found from cross-validation leads | ||
+ | to disastrous model performances on some classes e.g. on Imagenet with a resnet50, the “barn spider” classification test accuracy falls from 68% to 46% only by introducing random crop DA during | ||
+ | training. Even more surprising, such performance drop also appears when introducing uninformative | ||
+ | regularization techniques such as weight decay. Those results demonstrate that our search for ever | ||
+ | increasing generalization performance -averaged over all classes and samples- has left us with models | ||
+ | and regularizers that silently sacrifice performances on some classes. This scenario can become dangerous when deploying a model on downstream tasks e.g. an Imagenet pre-trained resnet50 deployed | ||
+ | on INaturalist sees its performances fall from 70% to 30% on class #8889 when introducing random | ||
+ | crop DA during the Imagenet pre-training phase. Those results demonstrate that designing novel | ||
+ | regularizers without class-dependent bias remains an open research question. | ||
+ | |||
+ | <box 99% orange> | ||
+ | Randall Balestriero, | ||
+ | |||
+ | [[http:// | ||
+ | [[http:// | ||
+ | [[http:// | ||
+ | </ | ||
+ | |||
+ | @inproceedings{balestriero-2022, | ||
+ | author = {Balestriero, | ||
+ | booktitle = {Advances in Neural Information Processing Systems}, | ||
+ | editor = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D. and Cho, K. and Oh, A.}, | ||
+ | pages = {37878--37891}, | ||
+ | publisher = {Curran Associates, Inc.}, | ||
+ | title = {The Effects of Regularization and Data Augmentation are Class Dependent}, | ||
+ | volume = {35}, | ||
+ | year = {2022}, | ||
+ | url = {http:// | ||
+ | } |