Related papers: 360$^\circ$ from a Single Camera: A Few-Shot Appro…
Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…
Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…
This paper presents an approach for applying camera perception techniques to spinning LiDAR data. To improve the robustness of long-term change detection from a 3D LiDAR, range and intensity information are rendered into virtual…
Nodule segmentation from breast ultrasound images is challenging yet essential for the diagnosis. Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. Unlike existing weakly-supervised…
Semantic segmentation is a crucial step in many Earth observation tasks. Large quantity of pixel-level annotation is required to train deep networks for semantic segmentation. Earth observation techniques are applied to varieties of…
Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations. Recent progress in fewshot…
We present a self-supervised learning approach for the semantic segmentation of lidar frames. Our method is used to train a deep point cloud segmentation architecture without any human annotation. The annotation process is automated with…
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…
Training a computer vision system to segment a novel class typically requires collecting and painstakingly annotating lots of images with objects from that class. Few-shot segmentation techniques reduce the required number of images to…
LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point- or voxel-based methods as they often yield better performance than the traditional range view representation. In this work, we unveil several key…
Few-shot learning aims to handle previously unseen tasks using only a small amount of new training data. In preparing (or meta-training) a few-shot learner, however, massive labeled data are necessary. In the real world, unfortunately,…
Object detection with event cameras benefits from the sensor's low latency and high dynamic range. However, it is costly to fully label event streams for supervised training due to their high temporal resolution. To reduce this cost, we…
LiDAR is a crucial sensor in autonomous driving, commonly used alongside cameras. By exploiting this camera-LiDAR setup and recent advances in image representation learning, prior studies have shown the promising potential of image-to-LiDAR…
We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the meta-learning paradigm. We introduce a transductive…
Accurate school detection is essential for supporting education initiatives, including infrastructure planning and expanding internet connectivity to underserved areas. However, many regions around the world face challenges due to outdated,…
LiDAR is used in autonomous driving to provide 3D spatial information and enable accurate perception in off-road environments, aiding in obstacle detection, mapping, and path planning. Learning-based LiDAR semantic segmentation utilizes…
Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard…
Medical image segmentation has made significant progress in recent years. Deep learning-based methods are recognized as data-hungry techniques, requiring large amounts of data with manual annotations. However, manual annotation is expensive…
Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most…