Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

该研究提出了一种对抗自监督学习(ASSL)框架,旨在解决半监督3D动作识别问题。通过结合自监督学习与对抗学习,ASSL能够从大量未标记的骨骼序列中学习动作表征。文章指出直接应用自监督学习可能导致有标签和无标签样本的学习不一致,为此引入了邻居一致性策略,通过K近邻和信息聚合增强类别语义。此外,还提出了一种对抗正则化方法来对齐有监督和自监督学习的特征分布,提高模型的泛化能力。
摘要由CSDN通过智能技术生成

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

Abstract
自监督学习(SSL)已被证明在图像域中从未标记数据中学习表示非常有效。目前,针对三维动作识别的有效自监督方法还不多见,直接将SSL应用于半监督学习,存在从SSL学习到的表征与有监督学习任务不一致的问题。为解决这个问题。作者提出对抗自监督学习(ASSL),它通过领域关系提取和对抗学习把SSL和半监督方法结合。
Introduction
最近,SSL被提出通过骨骼图用来学习未标签序列的时间信息,但SSL把每一个样本都视作独立个体,因此忽视了样本中相似动作所共有的信息。
直接将SSL应用于半监督学习,存在自监督学习任务和有监督学习任务学习结果不一致的问题。受unsupervised domain adaptation (UDA)中对抗学习的启发,把adversarial learning与self-supervision结合进semi-supervised learning中。
main contributions:
1.我们为半监督3D动作识别提出了一个对抗自监督学习(ASSL)框架,它通过对抗学习和领域关系探索把SSL和半监督方法紧密的结合。
2.我们提出了一个新的自监督方案,i.e.,邻居一致性。通过研究领域的数据联系,模型能学习到不同的动作表征。
3.我们确定了直接将SSL应用于半监督学习,存在有标签样本与无标签样本学习结果不一致的问题。一个新颖的对抗正则化被提出将SSL与半监督算法结合,以对齐两者的特征分布,这能进一步的提升泛化能力。
problem frmulation
使用很少的标签数据在半监督3D动作识别。首先, X X X代表训练集。训练样本 x i ∈ X x_i\in X xiX是带有T帧的骨骼序列,与有监督3D动作识别不同,训练集被分为两部分:有标签集 X L X_L XL,无标签集 X U X_U XU。受 S 4 L S^4L S4L启发,我们提出了对抗自监督学习架构来学习两个训练集的不同动作表征。
neighborhood consistency
半监督3D动作识别的目的是学习有区别的动作表征从大量的无标签序列。然而,很难获得简洁的3D人类姿势。为解决这个问题,我们提出了一个高效的SSL策略,领域一致性,一吃增强潜在的类别语义的动作表征。
在这里插入图片描述
如图,我们首先应用skeleton inpainting学习无标签序列的时间信息。具体来说,编码器网络Encr把输入骨骼序列 x u x_u xu生成为时间特征 h u h_u hu。一个解码器网络Dec目标是填充输入序列的masked region,为了区分在动作分类(区别)和骨骼修补(回归),我们使用了一个翻译层,例如,一个线性层搭建两者特征空间的关系。线性层的样本 x u x_u xu的输出表示为 h ‾ u \overline{h}_u hu。在这个特征空间,我们应用K-nearest neighborFon从未标签训练集 X U X_U XU来选择K最近邻居。 x u x_u xu的邻居集被表示为 Ω x \Omega _x Ωx。一个信息聚合模型被提出老生成局部中心向量。我们使用多重感知机来分配每一个邻居样本的权值,评估他们的相似性,权值 α k \alpha _k αk计算如下:
在这里插入图片描述
上式 h ‾ u k \overline{h}^k_u huk是邻居样本 x u k x_u^k xuk被翻译的特征, M L P ( ) MLP() MLP()表示多重感知机,通过被计算的权重{ α 1 , . . . , α K \alpha_1,...,\alpha_K α1,...,αK},局部类中心 c u c_u cu被聚类为:
在这里插入图片描述

### Self-Ensemble Concept In the realm of machine learning, self-ensemble refers to a technique where multiple models are created from variations or augmentations of training data points. These models collectively contribute towards making predictions that can be more robust than those made by any single model alone[^1]. The ensemble is built using different snapshots of the same neural network at various stages during its training process. The core idea behind this approach lies in leveraging diverse perspectives provided by these varied instances of the model trained on slightly altered datasets derived through transformations like noise addition or dropout regularization techniques applied over original inputs. This diversity helps improve generalization capabilities while reducing variance across predictions. #### Applications in Machine Learning One prominent application area for self-ensembles involves semi-supervised learning scenarios wherein only limited labeled examples exist alongside abundant unlabeled ones available for use during training phases. By applying consistency regularization methods such as Mean Teacher (MT), Temporal Ensembling (TE), Virtual Adversarial Training (VAT), etc., one ensures stable performance even when dealing with scarce supervision signals. Another significant utilization pertains to unsupervised domain adaptation tasks aiming to transfer knowledge acquired within source domains characterized by ample annotated samples into target environments lacking sufficient labeling but sharing similar characteristics otherwise unobserved directly due to distributional shifts between them both spatially and temporally speaking. Additionally, self-ensemble has been successfully employed in improving adversarial robustness against carefully crafted attacks designed specifically targeting deep networks' vulnerabilities exposed under certain conditions leading potentially catastrophic failures unless properly mitigated beforehand via defensive mechanisms embedded throughout architecture design choices including preprocessing steps taken prior feeding raw input features into subsequent layers responsible ultimately producing final outputs after passing several intermediate computations along pathways connecting neurons together forming complex webs capable performing intricate pattern recognition feats beyond human comprehension levels achievable today thanks largely advances brought forth recent years particularly around computational power availability coupled efficient algorithms development enabling faster experimentation cycles yielding better results overall time frame considered historically relevant benchmarks established previously before current era commenced officially ushering new age artificial intelligence research endeavors worldwide spanning numerous disciplines ranging natural sciences social studies humanities arts culture technology engineering mathematics statistics physics chemistry biology medicine health care environmental sustainability energy resources management policy governance ethics law regulation compliance security privacy protection safety assurance quality control standards setting benchmark creation measurement evaluation assessment feedback improvement innovation disruption transformation evolution revolution renaissance enlightenment awakening consciousness expansion awareness elevation transcendence ascension liberation freedom empowerment autonomy sovereignty independence interdependence cooperation collaboration coordination synchronization harmonization integration synthesis analysis decomposition reconstruction deconstruction construction building designing creating imagining envisioning conceptualizing theorizing hypothesizing experimenting validating verifying falsifying refuting rebutting arguing debating discussing communicating collaborating cooperating coordinating synchronizing harmonizing integrating synthesizing analyzing decomposing reconstructing deconstructing constructing building designing creating imagining envisioning conceptualizing theorizing hypothesizing experimenting validating verifying falsifying refuting rebutting arguing debating discussing communicating. ```python import numpy as np def create_self_ensemble(model, X_train, y_train=None): ensembles = [] # Create multiple versions of the dataset with slight modifications. for i in range(5): modified_X = apply_transformation(X_train.copy()) if y_train is not None: ensemble_model = train_model(model, modified_X, y_train) else: ensemble_model = train_unsupervised_model(model, modified_X) ensembles.append(ensemble_model) return ensembles def predict_with_self_ensemble(ensembles, X_test): all_predictions = [] for model in ensembles: prediction = model.predict(X_test) all_predictions.append(prediction) averaged_prediction = np.mean(all_predictions, axis=0) return averaged_prediction ```
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值