CVPR physical is back and we’re delighted to say we will be there in Louisiana to listen and learn, share our latest work and talk about out open positions and internships. We want to catch up with old friends and acquaintances and make some new ones. From across NAVER we have 17 papers at this year’s conference and we’ll be giving some invited workshop keynotes. NAVER LABS Europe specific material is listed below but, if you’re there, come visit the NAVER LINE booth 1529 to meet the team, discover what the new NAVER HQ looks like – the world’s first ever robot friendly building! – learn about computer vision research at WEBTOON (the world’s #1 digital comic app), discover CLOVA AI core tech for user services and spend some time on the NAVER LABS Europe interactive demos.
O-Drum: Open-Domain Retrieval Under a Multi-Modal Setting workshop
Monday, June 20th, 11:05-11:40 CDT
Invited speaker Diane Larlus, principal research scientist and team lead in Computer Vision.
Diane also leads the chair on life-long representation learning within the French interdisciplinary AI institute MIAI in Grenoble.
NAVER LABS Europe papers:
Tuesday, June 21st (afternoon), 14:30 – 17: 00 CDT | Poster 1.2: 3D from single images session (Halls B2-C)
132. PUMP: pyramidal and uniqueness matching priors for unsupervised learning of local features
Jérome Revaud, Vincent Leroy, Philippe Weinzaepfel, Boris Chidlovskii
Abstract: Existing approaches for learning local image descriptors have shown remarkable achievements in a wide range of geometric tasks. However, most of them require per-pixel correspondence-level supervision, which is difficult to acquire at scale and in high quality. In this paper, we propose to explicitly integrate two matching priors in a single loss in order to learn local descriptors without supervision. Given two images depicting the same scene, we extract pixel descriptors and build a correlation volume. The first prior enforces the local consistency of matches in this volume via a pyramidal structure constructed iteratively at multiple scales using a non-parametric module. The second prior exploits the fact that each descriptor should match with at most one descriptor from the other image. We combine our unsupervised loss with a standard self-supervised loss trained from synthetic image augmentations. Feature descriptors learned by the proposed approach outperform their fully- and self-supervised counterparts on various geometric benchmarks such as visual localization and image matching, achieving state-of-the-art performance
[PDF] [supp]
Wednesday, June 22nd (Morning), 08:30 – 10:18 CDT, Oral 2.1.1: Recognition: Detection, Categorization, Retrieval (Great Hall A-D)
Deep visual geo-localization benchmark
Gabriele Berton, Riccardo Mereu, Gabriele Trivigno, Carlo Masone, Gabriela Csurka, Torsten Sattler, Barbara Caputo
Abstract: In this paper, we propose a new open-source benchmarking framework for Visual Geo-localization (VG) that allows to build, train, and test a wide range of commonly used architectures, with the flexibility to change individual components of a geo-localization pipeline. The purpose of this framework is twofold: i) gaining insights into how different components and design choices in a VG pipeline impact the final results, both in terms of performance (recall@N metric) and system requirements (such as execution time and memory consumption); ii) establish a systematic evaluation protocol for comparing different methods. Using the proposed framework, we perform a large suite of experiments which provide criteria for choosing backbone, aggregation and negative mining depending on the use-case and requirements. We also assess the impact of engineering techniques like pre/post-processing, data augmentation and image resizing, showing that better performance can be obtained through somewhat simple procedures: for example, downscaling the images’ resolution to 80% can lead to similar results with a 36% savings in extraction time and dataset storage requirement.
[PDF] [supp] [arXiv]
48. On the road to online adaptation for semantic image segmentation
Riccardo Volpi, Pau De Jorge, Gabriela Csurka Khedari, Diane Larlus
Abstract: We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation. The overall goal is fostering the development of adaptive learning systems that will continuously learn, without supervision, in ever-changing environments. Typical protocols that study adaptation algorithms for segmentation models are limited to few domains, adaptation happens offline, and human intervention is generally required, at least to annotate data for hyper-parameter tuning. We argue that such constraints are incompatible with algorithms that can continuously adapt to different real-world situations. To address this, we propose a protocol where models need to learn online, from sequences of temporally correlated images, requiring continuous, frame-by-frame adaptation. We accompany this new protocol with a variety of baselines to tackle the proposed formulation, as well as an extensive analysis of their behaviors, which can serve as a starting point for future research.
[PDF] [supp] [arXiv]
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.