Related papers: PMT-MAE: Dual-Branch Self-Supervised Learning with…

We propose a new semi-supervised learning method on face-related tasks based on Multi-Task Learning (MTL) and data distillation. The proposed method exploits multiple datasets with different labels for different-but-related tasks such as…

We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised manner. By exploiting the geometric…

Recent advancements in Diffusion Transformer (DiT) models have significantly improved 3D point cloud generation. However, existing methods primarily focus on local feature extraction while overlooking global topological information, such as…

We present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR). The MV-MR is based on the maximization of dependence between learnable embeddings from augmented and…

Recently, the community has made tremendous progress in developing effective methods for point cloud video understanding that learn from massive amounts of labeled data. However, annotating point cloud videos is usually notoriously…

Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during…

We present a novel and flexible architecture for point cloud segmentation with dual-representation iterative learning. In point cloud processing, different representations have their own pros and cons. Thus, finding suitable ways to…

3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic…

This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning…

Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to…

Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap…

Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…

Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…

Online knowledge distillation conducts knowledge transfer among all student models to alleviate the reliance on pre-trained models. However, existing online methods rely heavily on the prediction distributions and neglect the further…

We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and 3D data for weakly supervised point cloud segmentation. Research studies have shown that 2D and 3D features are complementary for point cloud segmentation.…

Pretrained language models (PLMs) such as BERT adopt a training paradigm which first pretrain the model in general data and then finetune the model on task-specific data, and have recently achieved great success. However, PLMs are notorious…

Skin lesion classification datasets often suffer from severe class imbalance, with malignant cases significantly underrepresented, leading to biased decision boundaries during deep learning training. We address this challenge using…

We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of dense annotations. Unfortunately, with extremely sparse…

Three-dimensional (3D) point cloud analysis has become central to applications ranging from autonomous driving and robotics to forestry and ecological monitoring. Although numerous deep learning methods have been proposed for point cloud…

Segmentation of plant point clouds to obtain high-precise morphological traits is essential for plant phenotyping. Although the fast development of deep learning has boosted much research on segmentation of plant point clouds, previous…