SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds
We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original point cloud without corruption. The encoder learns the high-level latent representations of the points clouds in a low-dimensional subspace and recovers the original structure. In this work, we have used Transformers and PointNet-based Autoencoders. The proposed framework also addresses some of the limitations of Transformers-based Masked Autoencoders which are prone to leakage of location information and uneven information density. We trained our models on the complete ShapeNet dataset and evaluated them on ModelNet40 as a downstream classification task. We have shown that the pretrained models achieved 0.5-1% higher classification accuracies than the networks trained from scratch. Furthermore, we also proposed VASP: Vector-Quantized Autoencoder for Self-supervised Representation Learning for Point Clouds that employs Vector-Quantization for discrete representation learning for Transformer-based autoencoders.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderQuantizationRepresentation LearningSelf-Supervised LearningSimilar Papers 제목 키워드 기반
SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models
Radiology Report Generation (R2Gen) demonstrates how Multi-modal Large Language Models (MLLMs) can automate the creation of accurate and coherent radiological reports. Existing methods often hallucinate details in text-b…
Causal Language ModelingHallucinationLanguage ModelingLanguage ModellingCP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
Self-supervised learning has not been fully explored for point cloud analysis. Current frameworks are mainly based on point cloud reconstruction. Given only 3D coordinates, such approaches tend to learn local geometric s…
Point cloud reconstructionSelf-Supervised LearningPerturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation
Large-scale point cloud semantic segmentation has wide applications. Current popular researches mainly focus on fully supervised learning which demands expensive and tedious manual point-wise annotation. Weakly super…
Self-Supervised LearningSemantic SegmentationWeakly-supervised LearningSERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning
Test-time reinforcement learning (TTRL) enables language models to self-evolve at inference time without labeled feedback. Existing methods rely on answer voting and therefore do not extend naturally to open-ended genera…
Reinforcement LearningGraph Self-supervised Learning with Accurate Discrepancy Learning
Self-supervised learning of graph neural networks (GNNs) aims to learn an accurate representation of the graphs in an unsupervised manner, to obtain transferable representations of them for diverse downstream tasks. Pred…
Contrastive LearningLink PredictionMolecular Property PredictionProperty Prediction+2