Related papers: HeAL3D: Heuristical-enhanced Active Learning for 3…
The performance of learning-based algorithms improves with the amount of labelled data used for training. Yet, manually annotating data is particularly difficult for medical image segmentation tasks because of the limited expert…
Semantic segmentation of satellite imagery plays a vital role in land cover mapping and environmental monitoring. However, annotating large-scale, high-resolution satellite datasets is costly and time consuming, especially when covering…
Unsupervised aspect detection (UAD) aims at automatically extracting interpretable aspects and identifying aspect-specific segments (such as sentences) from online reviews. However, recent deep learning-based topic models, specifically…
Recent advancements in camera-based 3D object detection have introduced cross-modal knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging the precise geometric information in LiDAR point clouds. However,…
In many histopathology tasks, sample classification depends on morphological details in tissue or single cells that are only visible at the highest magnification. For a pathologist, this implies tedious zooming in and out, while for a…
Deep active learning (DAL) methods have shown significant improvements in sample efficiency compared to simple random sampling. While these studies are valuable, they nearly always assume that optimal DAL hyperparameter (HP) settings are…
The application of vision-based multi-view environmental perception system has been increasingly recognized in autonomous driving technology, especially the BEV-based models. Current state-of-the-art solutions primarily encode image…
Deep Learning (DL) has brought significant advances to robotics vision tasks. However, most existing DL methods have a major shortcoming, they rely on a static inference paradigm inherent in traditional computer vision pipelines. On the…
Dense regression is a widely used approach in computer vision for tasks such as image super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation and labeling makes it challenging to achieve accurate results.…
Creating mobile robots which are able to find and manipulate objects in large environments is an active topic of research. These robots not only need to be capable of searching for specific objects but also to estimate their poses often…
Regression is a fundamental prediction task common in data-centric engineering applications that involves learning mappings between continuous variables. In many engineering applications (e.g.\ structural health monitoring), feature-label…
3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot perception, and to that end, we introduce a method for jointly…
Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal sequences while…
Active Learning (AL) addresses the high costs of collecting human annotations by strategically annotating the most informative samples. However, for subjective NLP tasks, incorporating a wide range of perspectives in the annotation process…
Deep Learning (DL) based methods for object detection achieve remarkable performance at the cost of computationally expensive training and extensive data labeling. Robots embodiment can be exploited to mitigate this burden by acquiring…
In recent years, knowledge distillation (KD) has been widely used to derive efficient models. Through imitating a large teacher model, a lightweight student model can achieve comparable performance with more efficiency. However, most…
Deep neural networks based object detectors have shown great success in a variety of domains like autonomous vehicles, biomedical imaging, etc. It is known that their success depends on a large amount of data from the domain of interest.…
Despite the fact that object detection, 3D pose estimation, and sub-category recognition are highly correlated tasks, they are usually addressed independently from each other because of the huge space of parameters. To jointly model all of…
Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised…
Most 3d human pose estimation methods assume that input -- be it images of a scene collected from one or several viewpoints, or from a video -- is given. Consequently, they focus on estimates leveraging prior knowledge and measurement by…