Related papers: Learning from Mistakes: Self-Regularizing Hierarch…

Large language models (LLMs) recently exhibited remarkable reasoning capabilities on solving math problems. To further improve their reasoning capabilities, this work explores whether LLMs can LEarn from MistAkes (LEMA), akin to the human…

In machine learning, classification is usually seen as a function approximation problem, where the goal is to learn a function that maps input features to class labels. In this paper, we propose a novel clustering and classification…

Semantic segmentation of LiDAR point clouds has been widely studied in recent years, with most existing methods focusing on tackling this task using a single scan of the environment. However, leveraging the temporal stream of observations…

The integration of machine learning models in various real-world applications is becoming more prevalent to assist humans in their daily decision-making tasks as a result of recent advancements in this field. However, it has been discovered…

Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer from severe training…

Discriminative and generative vision models excel in their respective domains but remain semantically misaligned, hindering progress toward unified visual learning. We introduce LEASE (LEArning from SEmantic Dictionaries), a self-supervised…

Decentralized learning (DL) enables collaborative machine learning (ML) without a central server, making it suitable for settings where training data cannot be centrally hosted. We introduce Mosaic Learning, a DL framework that decomposes…

Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…

Deep neural networks are susceptible to learn biased models with entangled feature representations, which may lead to subpar performances on various downstream tasks. This is particularly true for under-represented classes, where a lack of…

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods…

A main bottleneck of learning-based robotic scene understanding methods is the heavy reliance on extensive annotated training data, which often limits their generalization ability. In LiDAR panoptic segmentation, this challenge becomes even…

Semantic segmentation for robotic systems can enable a wide range of applications, from self-driving cars and augmented reality systems to domestic robots. We argue that a spherical representation is a natural one for egocentric…

In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle's surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the…

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

Accurate localization is a fundamental requirement for autonomous robots operating in indoor environments. Scene graphs encode the spatial structure of an environment as a hierarchy of semantic entities and their relationships, and can be…

Panoptic segmentation aims to address semantic and instance segmentation simultaneously in a unified framework. However, an efficient solution of panoptic segmentation in applications like autonomous driving is still an open research…

We present a novel post-processing tool for semantic segmentation of LiDAR point cloud data, called LidarMetaSeg, which estimates the prediction quality segmentwise. For this purpose we compute dispersion measures based on network…

3D laser scanning by LiDAR sensors plays an important role for mobile robots to understand their surroundings. Nevertheless, not all systems have high resolution and accuracy due to hardware limitations, weather conditions, and so on.…

We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a…