Related papers: Keypoint Autoencoders: Learning Interest Points of…

The expensive annotation cost is notoriously known as the main constraint for the development of the point cloud semantic segmentation technique. Active learning methods endeavor to reduce such cost by selecting and labeling only a subset…

Sequential sensor data is generated in a wide variety of practical applications. A fundamental challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent…

The autoencoder is an artificial neural network model that learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for…

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Fast and efficient semantic segmentation of large-scale LiDAR point clouds is a fundamental problem in autonomous driving. To achieve this goal, the existing point-based methods mainly choose to adopt Random Sampling strategy to process…

LiDAR-based 3D point cloud recognition has been proven beneficial in various applications. However, the sparsity and varying density pose a significant challenge in capturing intricate details of objects, particularly for medium-range and…

Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e.g. elbow, digit, abstract geometric shape) appears only once in an image. This greatly limits their applicability, as each…

Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable…

We present a novel approach to learning a point-wise, meaningful embedding for point-clouds in an unsupervised manner, through the use of neural-networks. The domain of point-cloud processing via neural-networks is rapidly evolving, with…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE development has been the lack of high-quality performance metrics,…

In the majority of executive domains, a notion of normality is involved in most strategic decisions. However, few data-driven tools that support strategic decision-making are available. We introduce and extend the use of autoencoders to…

Sketch recognition allows natural and efficient interaction in pen-based interfaces. A key obstacle to building accurate sketch recognizers has been the difficulty of creating large amounts of annotated training data. Several authors have…

Diagnosis based on medical images, such as X-ray images, often involves manual annotation of anatomical keypoints. However, this process involves significant human efforts and can thus be a bottleneck in the diagnostic process. To fully…

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud…

Conventional point cloud semantic segmentation methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information. However, the over-reliance on these class-agnostic…

Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of the prompts. We also empirically observe that conventional…

With the great progress of 3D sensing and acquisition technology, the volume of point cloud data has grown dramatically, which urges the development of efficient point cloud compression methods. In this paper, we focus on the task of…

Autoencoders offer a general way of learning low-dimensional, non-linear representations from data without labels. This is achieved without making any particular assumptions about the data type or other domain knowledge. The generality and…

We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online point-wise clustering method with a simplified equal class-size…