Related papers: Contrastive Embedding Distribution Refinement and …

Recently, representation learning with contrastive learning algorithms has been successfully applied to challenging unlabeled datasets. However, these methods are unable to distinguish important features from unimportant ones under simply…

Clustering continues to be a significant and challenging task. Recent studies have demonstrated impressive results by applying clustering to feature representations acquired through self-supervised learning, particularly on small datasets.…

How to extract significant point cloud features and estimate the pose between them remains a challenging question, due to the inherent lack of structure and ambiguous order permutation of point clouds. Despite significant improvements in…

We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as point clouds, spectral…

The majority of point cloud registration methods currently rely on extracting features from points. However, these methods are limited by their dependence on information obtained from a single modality of points, which can result in…

Deep learning techniques for point cloud data have demonstrated great potentials in solving classical problems in 3D computer vision such as 3D object classification and segmentation. Several recent 3D object classification methods have…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

Using search engines for web image retrieval is a tempting alternative to manual curation when creating an image dataset, but their main drawback remains the proportion of incorrect (noisy) samples retrieved. These noisy samples have been…

To deal with the exhausting annotations, self-supervised representation learning from unlabeled point clouds has drawn much attention, especially centered on augmentation-based contrastive methods. However, specific augmentations hardly…

Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level…

In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity…

End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet, or the more recent point cloud transformer -- and its variants --…

3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have advanced novel-view synthesis. Recent methods extend multi-view 2D segmentation to 3D, enabling instance/semantic segmentation for better scene understanding. A key…

3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and…

Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc. With the boost of the number of points in the data, how to efficiently…

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

This paper presents an effective few-shot point cloud semantic segmentation approach for real-world applications. Existing few-shot segmentation methods on point cloud heavily rely on the fully-supervised pretrain with large annotated…

Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness and a probabilistic interpretation. Recently, after the…

State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been…

3D perception in LiDAR point clouds is crucial for a self-driving vehicle to properly act in 3D environment. However, manually labeling point clouds is hard and costly. There has been a growing interest in self-supervised pre-training of 3D…