Related papers: Keypoint Autoencoders: Learning Interest Points of…

We address a core problem of computer vision: Detection and description of 2D feature points for image matching. For a long time, hand-crafted designs, like the seminal SIFT algorithm, were unsurpassed in accuracy and efficiency. Recently,…

CLIP's success has demonstrated that prompt tuning can achieve robust cross-modal semantic alignment for tasks ranging from open-domain recognition to fine-grained classification. However, redundant or weakly relevant feature components…

Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable…

Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…

In the last decade, driven also by the availability of an unprecedented computational power and storage capabilities in cloud environments we assisted to the proliferation of new algorithms, methods, and approaches in two areas of…

LiDAR panoptic segmentation is a newly proposed technical task for autonomous driving. In contrast to popular end-to-end deep learning solutions, we propose a hybrid method with an existing semantic segmentation network to extract semantic…

Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the…

Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to…

The large language models have achieved superior performance on various natural language tasks. One major drawback of such approaches is they are resource-intensive in fine-tuning new datasets. Soft-prompt tuning presents a…

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

In recent years, we have witnessed the presence of point cloud data in many aspects of our life, from immersive media, autonomous driving to healthcare, although at the cost of a tremendous amount of data. In this paper, we present an…

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.…

We propose a new fast fully unsupervised method to discover semantic patterns. Our algorithm is able to hierarchically find visual categories and produce a segmentation mask where previous methods fail. Through the modeling of what is a…

Current semantic segmentation approaches for point cloud scenes heavily rely on manual labeling, while research on unsupervised semantic segmentation methods specifically for raw point clouds is still in its early stages. Unsupervised point…

In recent years, with the development of computing resources and LiDAR, point cloud semantic segmentation has attracted many researchers. For the sparsity of point clouds, although there is already a way to deal with sparse convolution,…

We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained…

The estimation of viewpoints and keypoints effectively enhance object detection methods by extracting valuable traits of the object instances. While the output of both processes differ, i.e., angles vs. list of characteristic points, they…

Autoencoders are powerful machine learning models used to compress information from multiple data sources. However, autoencoders, like all artificial neural networks, are often unidentifiable and uninterpretable. This research focuses on…

A successful point cloud registration often lies on robust establishment of sparse matches through discriminative 3D local features. Despite the fast evolution of learning-based 3D feature descriptors, little attention has been drawn to the…

Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint…