pith. sign in

arxiv: 2009.03632 · v1 · pith:W5DXLAHXnew · submitted 2020-09-08 · 💻 cs.LG · cs.AI· cs.CV· stat.ML

Imbalanced Continual Learning with Partitioning Reservoir Sampling

classification 💻 cs.LG cs.AIcs.CVstat.ML
keywords distributionlearningsamplingbalancedchallengeclassificationcontinualdatasets
0
0 comments X
read the original abstract

Continual learning from a sequential stream of data is a crucial challenge for machine learning research. Most studies have been conducted on this topic under the single-label classification setting along with an assumption of balanced label distribution. This work expands this research horizon towards multi-label classification. In doing so, we identify unanticipated adversity innately existent in many multi-label datasets, the long-tailed distribution. We jointly address the two independently solved problems, Catastropic Forgetting and the long-tailed label distribution by first empirically showing a new challenge of destructive forgetting of the minority concepts on the tail. Then, we curate two benchmark datasets, COCOseq and NUS-WIDEseq, that allow the study of both intra- and inter-task imbalances. Lastly, we propose a new sampling strategy for replay-based approach named Partitioning Reservoir Sampling (PRS), which allows the model to maintain a balanced knowledge of both head and tail classes. We publicly release the dataset and the code in our project page.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.