Generative Hard Example Augmentation for Semantic Point Cloud Segmentation
The recent progress in semantic point cloud segmentation is attributed to deep networks, which require a large amount of point cloud data for training. However, how to collect substantial point-wise annotations of the point clouds at affordable cost for the end-to-end network training still needs to be solved. In this paper, we propose Generative Hard Example Augmentation (GHEA) to achieve novel examples of point clouds, which enrich the data for training the segmentation network. Firstly, GHEA employs the generative network to embed the discrepancy between the point clouds into the latent space. From the latent space, we sample multiple discrepancies for reshaping a point cloud to various examples, contributing to the richness of the training data. Secondly, GHEA mixes the reshaped point clouds by respecting their segmentation errors. This mixup allows the reshaped point clouds, which are difficult to segment, to join as the challenging example for network training. We evaluate the effectiveness of GHEA, which helps the popular segmentation networks to improve the performances.
Code (0)
등록된 구현이 없습니다.
Tasks
Point Cloud SegmentationSegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated…
ClusteringImage RetrievalMetric LearningRetrievalAdversarial Semantic Data Augmentation for Human Pose Estimation
Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and near…
Data AugmentationDiversityPose EstimationGLASS: Geometric Latent Augmentation for Shape Spaces
We investigate the problem of training generative models on a very sparse collection of 3D models. We use geometrically motivated energies to augment and thus boost a sparse collection of example (training) models. We an…
validReal3D-Aug: Point Cloud Augmentation by Placing Real Objects with Occlusion Handling for 3D Detection and Segmentation
Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose …
3D Object DetectionData AugmentationObjectobject-detection+4Generative Code Modeling with Graphs
Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel mod…
Structured Prediction