Improving Few-Shot Object Detection with Object Part Proposals

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Our dataset consists of very high-resolution aerial images (50cm) and a digital elevation model (50cm) that covers approx. 2300 km2 of land above 2000m altitude in the southwestern part of Switzerland. Our land cover labels focus on alpine land cover that ...

Urban planners are increasingly interested in understanding what makes a neighbourhood pleasant and liveable. In this paper, we use the overhead perspective as a new way to describe and understand liveability of city neighborhoods. We predict building qual ...

The detection of landmarks or patterns is of interest for extracting features in biological images. Hence, algorithms for finding these keypoints have been extensively investigated in the literature, and their localization and detection properties are well ...

A two-platform measurement system for realizing airborne thermography of the Lake Surface Water Temperature (LSWT) with ~0.8 m pixel resolution (sub-pixel satellite scale) is presented. It consists of a tethered Balloon Launched Imaging and Monitoring Plat ...

Unmanned Aerial Vehicles are becoming increasingly popular for a broad variety of tasks ranging from aerial imagery to objects delivery. With the expansion of the areas, where drones can be efficiently used, the collision risk with other flying objects inc ...

Photolithography is one of the earliest technologies used to transfer patterns to a substrate. It is also known as optical lithography since it uses light to transfer the pattern. The main exposure techniques exist in the industry are projection printing, ...

This study deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel via supervised classification as a basis for automatic map generation. Recently, deep convolutional neural networks (CNNs) ...

We propose an approach for on-line detection of small Unmanned Aerial Vehicles (UAVs) and estimation of their relative positions and velocities in the 3D environment from a single moving camera in the context of sense and avoid systems. This problem is cha ...

In proximity lithography, interference and diffraction effects arise when printing small features because of the proximity gap. Different techniques are used in order to control and take advantage of theses effects. In this paper, the focus is set on the M ...

Curvilinear networks are prevalent in nature and span many different scales, ranging from micron-scale neural structures in the brain to petameter-scale dark-matter arbors binding massive galaxy clusters. Reliably reconstructing them in an automated fashio ...

The main challenge of new information technologies is to retrieve intelligible information from the large volume of digital data gathered every day. Among the variety of existing data sources, the satellites continuously observing the surface of the Earth ...

This study examines the effects of land-use policies and natural events on the evolution of two wooded pastures in the Jura Mountains in Switzerland between 1934 and 2000. The socioeconomic context and the local conditions were seen as major driving forces ...

We introduce a complete parameterization of the family of two-dimensional steerable wavelets that are polar-separable in the Fourier domain under the constraint of self-reversibility. These wavelets are constructed by multiorder generalized Riesz transform ...

Many classes of objects can now be successfully detected with statistical machine learning techniques. Faces, cars and pedestrians, have all been detected with low error rates by learning their appearance in a highly generic manner from extensive training ...

We propose a new learning strategy for object detection. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform base ...

This paper presents a semi-automatic and systematic computational approach intending to count and localize different species of trees in zones of dense forest. Comparative analysis of the application of multi-spectral high resolution images and aerial LIDA ...

Among all satellite imaging systems, Synthetic Aperture Radar (SAR) is useful for monitoring purposes, as they provide data at any time under all weather conditions. Today, three spaceborne SAR systems are operational, while by the end of 2007 three furthe ...

Improving Few-Shot Object Detection with Object Part Proposals

Chat with Graph Search

swissALPS: a Dataset for Imbalanced Land Cover Mapping in Alpine Regions

Liveability from Above: Understanding Quality of Life with Overhead Imagery and Deep Neural Networks

Angular Accuracy of Steerable Feature Detectors

Achieving high-resolution thermal imagery in low-contrast lake surface waters by aerial remote sensing and image registration

Vision-based detection of aircrafts and UAVs

Limitations of Proximity Lithography Printing : Simulations, Experiments, and Applications

Learning Aerial Image Segmentation from Online Maps

Vision-Based Unmanned Aerial Vehicle Detection and Tracking for Sense and Avoid Systems

Coherence management in lithography printing systems

Automated Reconstruction of Evolving Curvilinear Tree Structures

Semi-supervised and unsupervised kernel-based novelty detection with application to remote sensing images

A Contextual Analysis of Land-Use and Vegetation Changes in Two Wooded Pastures in the Swiss Jura Mountains

A Unifying Parametric Framework for 2D Steerable Wavelet Transforms

Learning to Detect Objects with Minimal Supervision

A Real-Time Deformable Detector

Semi-automatic Use of High Resolution Images and Digital Elevation Models for Counting and Identification of Forest Trees

Time-Varying Segmentation for Mapping of Land Cover Changes