PointSmile: Point Self-supervised Learning via Curriculum Mutual Information
Self-supervised learning is attracting wide attention in point cloud processing. However, it is still not well-solved to gain discriminative and transferable features of point clouds for efficient training on downstream tasks, due to their natural sparsity and irregularity. We propose PointSmile, a reconstruction-free self-supervised learning paradigm by maximizing curriculum mutual information (CMI) across the replicas of point cloud objects. From the perspective of how-and-what-to-learn, PointSmile is designed to imitate human curriculum learning, i.e., starting with an easy curriculum and gradually increasing the difficulty of that curriculum. To solve "how-to-learn", we introduce curriculum data augmentation (CDA) of point clouds. CDA encourages PointSmile to learn from easy samples to hard ones, such that the latent space can be dynamically affected to create better embeddings. To solve "what-to-learn", we propose to maximize both feature- and class-wise CMI, for better extracting discriminative features of point clouds. Unlike most of existing methods, PointSmile does not require a pretext task, nor does it require cross-modal data to yield rich latent representations. We demonstrate the effectiveness and robustness of PointSmile in downstream tasks including object classification and segmentation. Extensive results show that our PointSmile outperforms existing self-supervised methods, and compares favorably with popular fully-supervised methods on various standard architectures.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation
Self-supervised neural machine translation (SSNMT) jointly learns to identify and select suitable training data from comparable (rather than parallel) corpora and to translate, in a way that the two tasks support each ot…
DenoisingMachine TranslationTranslationSelf-Induced Curriculum Learning in Neural Machine Translation
Self-supervised neural machine translation (SS-NMT) learns how to extract/select suitable training data from comparable (rather than parallel) corpora and how to translate, in a way that the two tasks support each other …
DenoisingMachine TranslationNMTTranslationCASSL: Curriculum Accelerated Self-Supervised Learning
Recent self-supervised learning approaches focus on using a few thousand data points to learn policies for high-level, low-dimensional action spaces. However, scaling this framework for high-dimensional control require e…
Self-Supervised LearningVariational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills
Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximizat…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot NavigationUnsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction
Semantic 3D keypoints are category-level semantic consistent points on 3D objects. Detecting 3D semantic keypoints is a foundation for a number of 3D vision tasks but remains challenging, due to the ambiguity of semantic…