TWIST: Two-Way Inter-Label Self-Training for Semi-Supervised 3D Instance Segmentation
We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation. To leverage the unlabeled data to boost model performance, we present a novel Two-Way Inter-label Self-Training framework named TWIST. It exploits inherent correlations between semantic understanding and instance information of a scene. Specifically, we consider two kinds of pseudo labels for semantic- and instance-level supervision. Our key design is to provide object-level information for denoising pseudo labels and make use of their correlation for two-way mutual enhancement, thereby iteratively promoting the pseudo-label qualities. TWIST attains leading performance on both ScanNet and S3DIS, compared to recent 3D pre-training approaches, and can cooperate with them to further enhance performance, e.g., +4.4% AP50 on 1%-label ScanNet data-efficient benchmark. Code is available at https://github.com/dvlab-research/TWIST.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Instance SegmentationDenoisingInstance SegmentationPseudo LabelSemantic SegmentationSimilar Papers 제목 키워드 기반
Self-Supervised Learning by Estimating Twin Class Distributions
We present TWIST, a simple and theoretically explainable self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a soft…
Fine-Grained Image ClassificationImage ClassificationRepresentation LearningSelf-Supervised Image Classification+4Rethinking Deep Clustering Paradigms: Self-Supervision Is All You Need
The recent advances in deep clustering have been made possible by significant progress in self-supervised and pseudo-supervised learning. However, the trade-off between self-supervision and pseudo-supervision can give ri…
AllClusteringDeep ClusteringA Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train …
text-to-speechText to SpeechEnhancing semi-supervised learning via self-interested coalitional learning
Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rel…
Proceedings of the fourth "international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques" (iTWIST'18)
The iTWIST workshop series aim at fostering collaboration between international scientific teams for developing new theories, applications and generalizations of low-complexity models. These events emphasize disseminatio…
Philosophy