Related papers: Interpreting Hidden Semantics in the Intermediate …

We explore a new class of end-to-end learnable models wherein data processing nodes (or network layers) are defined in terms of desired behavior rather than an explicit forward function. Specifically, the forward function is implicitly…

Point cloud data now are popular data representations in a number of three-dimensional (3D) vision research realms. However, due to the limited performance of sensors and sensing noise, the raw data usually suffer from sparsity, noise, and…

Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges…

Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large…

3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from the part…

Traditionally, CNN models possess hierarchical structures and utilize the feature mapping of the last layer to obtain the prediction output. However, it can be difficulty to settle the optimal network depth and make the middle layers learn…

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…

While deeply supervised networks are common in recent literature, they typically impose the same learning objective on all transitional layers despite their varying representation powers. In this paper, we propose Hierarchically Supervised…

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the…

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would provide insights into the question of what a deep learning system has internally detected as relevant on the…

Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current evaluation methodologies lack transparency, particularly in…

Deep learning is increasingly being used to perform machine vision tasks such as classification, object detection, and segmentation on 3D point cloud data. However, deep learning inference is computationally expensive. The limited…

In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel…

Understanding dynamic 3D environment is crucial for robotic agents and many other applications. We propose a novel neural network architecture called $MeteorNet$ for learning representations for dynamic 3D point cloud sequences. Different…

The current deep neural network algorithm still stays in the end-to-end training supervision method like Image-Label pairs, which makes traditional algorithm is difficult to explain the reason for the results, and the prediction logic is…

One of the current key challenges in Explainable AI is in correctly interpreting activations of hidden neurons. It seems evident that accurate interpretations thereof would provide insights into the question what a deep learning system has…

The 3D scene understanding is mainly considered as a crucial requirement in computer vision and robotics applications. One of the high-level tasks in 3D scene understanding is semantic segmentation of RGB-Depth images. With the availability…

Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still require long training…

ML-based systems are software systems that incorporates machine learning components such as Deep Neural Networks (DNNs) or Large Language Models (LLMs). While such systems enable advanced features such as high performance computer vision,…