FUSSL: Fuzzy Uncertain Self Supervised Learning
FUSSL: Fuzzy Uncertain Self Supervised Learning
复制标题
DOI：
10.1109/wacv56688.2023.00282
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
S. Mohamadi;Gianfranco Doretto;D. Adjeroh
中科院分区：
文献类型：
--
作者：
S. Mohamadi;Gianfranco Doretto;D. Adjeroh
自监督学习（SSL）已经成为一种非常成功的技术，可以利用未标记数据的力量，而无需注释。一些成熟的方法正在发展，目标是超越相对成功的监督替代方法。与深度表示学习中的其他学科类似，SSL的一个主要问题是不同设置下方法的鲁棒性。在本文中，我们第一次认识到SSL的基本限制来自使用一个单一的监督信号。为了解决这个问题，我们利用不确定性表示的力量，为任何SSL基线设计一个强大的和通用的标准分层学习/训练协议，无论他们的假设和方法。从本质上讲，使用信息瓶颈原理，我们将特征学习分解为两个阶段的训练过程，每个阶段都有一个不同的监督信号。这种双重监督方法分为两个关键步骤：1）对数据增强的不变性强制，以及2）模糊伪标记（硬注释和软注释）。这个简单而有效的协议，使跨类/集群特征学习，是通过初始训练的整体模型，通过不变性执法数据增强作为第一个训练阶段，然后分配模糊标签的原始样本的第二个训练阶段。我们考虑了具有双重监督的多种替代场景，并评估了我们的方法在最近基线上的有效性，涵盖四种不同的SSL范例，包括几何基线、对比基线、非对比基线和硬/软白化（冗余减少）基线。我们在多个设置下进行了广泛的实验，以表明所提出的训练协议始终提高了以前基线的性能，而与其各自的基本原理无关。
Self supervised learning (SSL) has become a very successful technique to harness the power of unlabeled data, with no annotation effort. A number of developed approaches are evolving with the goal of outperforming supervised alternatives, which have been relatively successful. Similar to some other disciplines in deep representation learning, one main issue in SSL is robustness of the approaches under different settings. In this paper, for the first time, we recognise the fundamental limits of SSL coming from the use of a single-supervisory signal. To address this limitation, we leverage the power of uncertainty representation to devise a robust and general standard hierarchical learning/training protocol for any SSL baseline, regardless of their assumptions and approaches. Essentially, using the information bottleneck principle, we decompose feature learning into a two-stage training procedure, each with a distinct supervision signal. This double supervision approach is captured in two key steps: 1) invariance enforcement to data augmentation, and 2) fuzzy pseudo labeling (both hard and soft annotation). This simple, yet, effective protocol which enables cross-class/cluster feature learning, is instantiated via an initial training of an ensemble of models through invariance enforcement to data augmentation as first training phase, and then assigning fuzzy labels to the original samples for the second training phase. We consider multiple alternative scenarios with double supervision and evaluate the effectiveness of our approach on recent baselines, covering four different SSL paradigms, including geometrical, contrastive, non-contrastive, and hard/soft whitening (redundancy reduction) baselines. We performed extensive experiments under multiple settings to show that the proposed training protocol consistently improves the performance of the former baselines, independent of their respective underlying principles.