Papers with Code 아카이브
Point Cloud Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 2
- 보존된 평가 기록
- 25
Point Cloud Classification is a task involving the classification of unordered 3D point sets (point clouds).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Local region-learning modules for point cloud classification
Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surface
EPiC: Ensemble of Partial Point Clouds for Robust Classification
Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network
Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space
PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees
CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mapping
S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification
PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis
Dynamic Local Feature Aggregation for Learning on Point Clouds
Implicit Convolutional Kernels for Steerable CNNs
Local Neighborhood Features for 3D Classification
TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
MATE: Masked Autoencoders are Online 3D Test-Time Learners
Do graph neural networks learn traditional jet substructure?
Equivariance with Learned Canonicalization Functions
Text2Model: Text-based Model Induction for Zero-shot Image Classification
Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classification
Jet tagging algorithm of graph network with HaarPooling message passing
Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks
Self-Distillation for Unsupervised 3D Domain Adaptation
Neural Attentive Circuits
APSNet: Attention Based Point Cloud Sampling
Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
A Simple Strategy to Provable Invariance via Orbit Mapping
Rethinking the compositionality of point clouds through regularization in the hyperbolic space
3DGTN: 3D Dual-Attention GLocal Transformer Network for Point Cloud Classification and Segmentation
SimpleView++: Neighborhood Views for Point Cloud Classification
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding
Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification
Boosting Point-BERT by Multi-choice Tokens
Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.