Related papers: Distillation with Contrast is All You Need for Sel…

Self-supervised learning attempts to learn representations from un-labeled data; it does so via a loss function that encourages the embedding of a point to be close to that of its augmentations. This simple idea performs remarkably well,…

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…

The scale and quality of point cloud datasets constrain the advancement of point cloud learning. Recently, with the development of multi-modal learning, the incorporation of domain-agnostic prior knowledge from other modalities, such as…

In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic…

Training a deep network policy for robot manipulation is notoriously costly and time consuming as it depends on collecting a significant amount of real world data. To work well in the real world, the policy needs to see many instances of…

The downstream accuracy of self-supervised methods is tightly linked to the proxy task solved during training and the quality of the gradients extracted from it. Richer and more meaningful gradients updates are key to allow self-supervised…

The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will…

Whilst contrastive learning yields powerful representations by matching different augmented views of the same instance, it lacks the ability to capture the similarities between different instances. One popular way to address this limitation…

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 structures and…

Both humans and deep learning models can recognize objects from 3D shapes depicted with sparse visual information, such as a set of points randomly sampled from the surfaces of 3D objects (termed a point cloud). Although deep learning…

As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…

Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous…

Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments.…

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary…

We propose a precise and efficient normal estimation method that can deal with noise and nonuniform density for unstructured 3D point clouds. Unlike existing approaches that directly take patches and ignore the local neighborhood…

This paper presents a study on improving human action recognition through the utilization of knowledge distillation, and the combination of CNN and ViT models. The research aims to enhance the performance and efficiency of smaller student…

Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…

As the development of 3D sensors, registration of 3D data (e.g. point cloud) coming from different kind of sensor is dispensable and shows great demanding. However, point cloud registration between different sensors is challenging because…

The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the…

Classification and segmentation of 3D point clouds are important tasks in computer vision. Because of the irregular nature of point clouds, most of the existing methods convert point clouds into regular 3D voxel grids before they are used…