论文标题
决斗：自适应副本消除工作记忆的自我监督学习
DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning
论文作者
论文摘要
在自我监督的学习（SSL）中，众所周知，碰撞的频繁出现，其中目标数据及其负样本共享同一类可以降低性能。特别是在现实世界中的数据（例如爬行数据或机器人收集的观察结果）中，由于数据中的重复项，碰撞可能更频繁地发生。为了解决这个问题，我们声称从内存中自适应分布的分布采样负面样本会使模型比直接从偏置数据集中采样的模型更稳定。在本文中，我们介绍了一个新颖的SSL框架，其灵感来自于人类工作记忆的启发，并具有自适应副本消除（决斗）。提出的框架成功地阻止了由于剧烈的阶层失衡而导致的下游任务性能从退化。
In Self-Supervised Learning (SSL), it is known that frequent occurrences of the collision in which target data and its negative samples share the same class can decrease performance. Especially in real-world data such as crawled data or robot-gathered observations, collisions may occur more often due to the duplicates in the data. To deal with this problem, we claim that sampling negative samples from the adaptively debiased distribution in the memory makes the model more stable than sampling from a biased dataset directly. In this paper, we introduce a novel SSL framework with adaptive Duplicate Elimination (DUEL) inspired by the human working memory. The proposed framework successfully prevents the downstream task performance from degradation due to a dramatic inter-class imbalance.
