PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such as PointMLP and Point Transformer, we find that a large portion of the performance gain is due to improved training strategies, i.e. data augmentation and optimization techniques, and increased model sizes rather than architectural innovations. Thus, the full potential of PointNet++ has yet to be explored. In this work, we revisit the classical PointNet++ through a systematic study of model training and scaling strategies, and offer two major contributions. First, we propose a set of improved training strategies that significantly improve PointNet++ performance.

Human pose estimation focuses on predicting body keypoints to analyze human motion. Event cameras provide high temporal resolution and low latency, enabling robust estimation under challenging conditions. However, most existing methods convert event streams into dense event frames, which adds extra computation and sacrifices the high temporal resolution of the event signal. In this work, we aim to exploit the spatiotemporal properties of event streams based on point cloud-based framework, designed to enhance human pose estimation performance. We design Event Temporal Slicing Convolution module to capture short-term dependencies across event slices, and combine it with Event Slice Sequencing module for structured temporal modeling. We also apply edge enhancement in point cloud-based event representation to enhance spatial edge information under sparse event conditions to further improve performance. Experiments on the DHP19 dataset show our proposed method consistently improves performance across three representative point cloud backbones: PointNet, DGCNN, and Point Transformer.

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 models achieve human - like performance in recognizing objects from 3D shapes, it remains unclear whether these models develop 3D shape representations similar to those used by human vision for object recognition. We hypothesize tha t training with 3D shapes enables models to form representations of local geometric structures in 3D shapes. However, their representations of global 3D object shapes may be limited. We conducted two human experiments systematically manipulating point density and object orientation (Experiment 1), and local geometric structure (Experiment 2) . Humans consistently performed well across all experimental conditions . We compared two types of deep learning models, one based on a convolution al neural network (DGCNN) and the other on visual transformers (point transformer), with human performance . We found that the point transformer model provide d a better account of human performance than the convolution - based model. The advantage mainly results from the mechanism in the point transformer model that support s hierarchical abstraction of 3D shapes.

Cone-beam computed tomography (CBCT) using only a few X-ray projection views enables faster scans with lower radiation dose, but the resulting severe under-sampling causes strong artifacts and poor spatial coverage. We address these challenges in a unified framework. First, we replace conventional UNet/ResNet encoders with TransUNet, a hybrid CNN-Transformer model. Convolutional layers capture local details, while self-attention layers enhance global context. We adapt TransUNet to CBCT by combining multi-scale features, querying view-specific features per 3D point, and adding a lightweight attenuation-prediction head. This yields Trans-CBCT, which surpasses prior baselines by 1.17 dB PSNR and 0.0163 SSIM on the LUNA16 dataset with six views. Second, we introduce a neighbor-aware Point Transformer to enforce volumetric coherence. This module uses 3D positional encoding and attention over k-nearest neighbors to improve spatial consistency. The resulting model, Trans$^2$-CBCT, provides an additional gain of 0.63 dB PSNR and 0.0117 SSIM. Experiments on LUNA16 and ToothFairy show consistent gains from six to ten views, validating the effectiveness of combining CNN-Transformer features with point-based geometry reasoning for sparse-view CBCT reconstruction.

Spiking Neural Networks (SNNs) offer an attractive and energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their sparse binary activation. When SNN meets Transformer, it shows great potential in 2D image processing. However, their application for 3D point cloud remains underexplored. To this end, we present Spiking Point Transformer (SPT), the first transformer-based SNN framework for point cloud classification. Specifically, we first design Queue-Driven Sampling Direct Encoding for point cloud to reduce computational costs while retaining the most effective support points at each time step. We introduce the Hybrid Dynamics Integrate-and-Fire Neuron (HD-IF), designed to simulate selective neuron activation and reduce over-reliance on specific artificial neurons. SPT attains state-of-the-art results on three benchmark datasets that span both real-world and synthetic datasets in the SNN domain. Meanwhile, the theoretical energy consumption of SPT is at least 6.4$\times$ less than its ANN counterpart.

PointNet is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet has been largely surpassed by recent networks such as PointMLP and Point Transformer, we find that a large portion of the performance gain is due to improved training strategies, i.e. data augmentation and optimization techniques, and increased model sizes rather than architectural innovations. Thus, the full potential of PointNet has yet to be explored. In this work, we revisit the classical PointNet through a systematic study of model training and scaling strategies, and offer two major contributions. First, we propose a set of improved training strategies that significantly improve PointNet performance.

This study introduces a federated learning-based approach to predict HER2 status from hematoxylin and eosin (HE)-stained whole slide images (WSIs), reducing costs and speeding up treatment decisions. To address label imbalance and feature representation challenges in multisite datasets, a point transformer is proposed, incorporating dynamic label distribution, an auxiliary classifier, and farthest cosine sampling. Extensive experiments demonstrate state-of-the-art performance across four sites (2687 WSIs) and strong generalization to two unseen sites (229 WSIs).

Point Transformers are near state-of-the-art models for classification, segmentation, and detection tasks on Point Cloud data. They utilize a self attention based mechanism to model large range spatial dependencies between multiple point sets. In this project we explore two things: classification performance of these attention based networks on ModelNet10 dataset and then, we use the trained model to classify 3D MNIST dataset after finetuning. We also train the model from scratch on 3D MNIST dataset to compare the performance of finetuned and from-scratch model on the MNIST dataset. We observe that since the two datasets have a large difference in the degree of the distributions, transfer learned models do not outperform the from-scratch models in this case. Although we do expect transfer learned models to converge faster since they already know the lower level edges, corners, etc features from the ModelNet10 dataset.

Conventional machine learning algorithms have traditionally been designed under the assumption that input data follows a vector-based format, with an emphasis on vector-centric paradigms. However, as the demand for tasks involving set-based inputs has grown, there has been a paradigm shift in the research community towards addressing these challenges. In recent years, the emergence of neural network architectures such as Deep Sets and Transformers has presented a significant advancement in the treatment of set-based data. These architectures are specifically engineered to naturally accommodate sets as input, enabling more effective representation and processing of set structures. Consequently, there has been a surge of research endeavors dedicated to exploring and harnessing the capabilities of these architectures for various tasks involving the approximation of set functions. This comprehensive survey aims to provide an overview of the diverse problem settings and ongoing research efforts pertaining to neural networks that approximate set functions. By delving into the intricacies of these approaches and elucidating the associated challenges, the survey aims to equip readers with a comprehensive understanding of the field. Through this comprehensive perspective, we hope that researchers can gain valuable insights into the potential applications, inherent limitations, and future directions of set-based neural networks. Indeed, from this survey we gain two insights: i) Deep Sets and its variants can be generalized by differences in the aggregation function, and ii) the behavior of Deep Sets is sensitive to the choice of the aggregation function. From these observations, we show that Deep Sets, one of the well-known permutation-invariant neural networks, can be generalized in the sense of a quasi-arithmetic mean.

Directly predicting human epidermal growth factor receptor 2 (HER2) status from widely available hematoxylin and eosin (HE)-stained whole slide images (WSIs) can reduce technical costs and expedite treatment selection. Accurately predicting HER2 requires large collections of multi-site WSIs. Federated learning enables collaborative training of these WSIs without gigabyte-size WSIs transportation and data privacy concerns. However, federated learning encounters challenges in addressing label imbalance in multi-site WSIs from the real world. Moreover, existing WSI classification methods cannot simultaneously exploit local context information and long-range dependencies in the site-end feature representation of federated learning. To address these issues, we present a point transformer with federated learning for multi-site HER2 status prediction from HE-stained WSIs. Our approach incorporates two novel designs. We propose a dynamic label distribution strategy and an auxiliary classifier, which helps to establish a well-initialized model and mitigate label distribution variations across sites. Additionally, we propose a farthest cosine sampling based on cosine distance. It can sample the most distinctive features and capture the long-range dependencies. Extensive experiments and analysis show that our method achieves state-of-the-art performance at four sites with a total of 2687 WSIs. Furthermore, we demonstrate that our model can generalize to two unseen sites with 229 WSIs.