Search Results for author: Diane Larlus

Found 28 papers, 9 papers with code

Improving the Generalization of Supervised Models

no code implementations30 Jun 2022 Mert Bulent Sariyildiz, Yannis Kalantidis, Karteek Alahari, Diane Larlus

Models trained with self-supervised learning (SSL) tend to generalize better than their supervised counterparts for transfer learning; yet, they still lag behind supervised models on IN1K.

Data Augmentation Self-Supervised Learning +1

On the Road to Online Adaptation for Semantic Image Segmentation

1 code implementation CVPR 2022 Riccardo Volpi, Pau de Jorge, Diane Larlus, Gabriela Csurka

We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation.

Semantic Segmentation Unsupervised Domain Adaptation

ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity

1 code implementation ICLR 2022 Ginger Delmas, Rafael Sampaio de Rezende, Gabriela Csurka, Diane Larlus

While the first provides rich and implicit context for the search, the latter explicitly calls for new traits, or specifies how some elements of the example image should be changed to retrieve the desired target image.

Image Retrieval

Learning Super-Features for Image Retrieval

1 code implementation ICLR 2022 Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis

Second, they are typically trained with a global loss that only acts on top of an aggregation of local features; by contrast, testing is based on local feature matching, which creates a discrepancy between training and testing.

Image Retrieval

Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval

no code implementations25 Oct 2021 Jonathan Munro, Michael Wray, Diane Larlus, Gabriela Csurka, Dima Damen

Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving videos based on their relevance to an unseen text query.

Unsupervised Domain Adaptation Video Retrieval

NeuralDiff: Segmenting 3D objects that move in egocentric videos

no code implementations19 Oct 2021 Vadim Tschernezki, Diane Larlus, Andrea Vedaldi

Given a raw video sequence taken from a freely-moving camera, we study the problem of decomposing the observed 3D scene into a static background and a dynamic foreground containing the objects that move in the video sequence.

Neural Rendering Semantic Segmentation

TLDR: Twin Learning for Dimensionality Reduction

1 code implementation18 Oct 2021 Yannis Kalantidis, Carlos Lassance, Jon Almazan, Diane Larlus

Dimensionality reduction methods are unsupervised approaches which learn low-dimensional spaces where some properties of the initial space, typically the notion of "neighborhood", are preserved.

Dimensionality Reduction Representation Learning +1

Probabilistic Embeddings for Cross-Modal Retrieval

1 code implementation CVPR 2021 Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende, Yannis Kalantidis, Diane Larlus

Instead, we propose to use Probabilistic Cross-Modal Embedding (PCME), where samples from the different modalities are represented as probabilistic distributions in the common embedding space.

Cross-Modal Retrieval

Concept Generalization in Visual Representation Learning

1 code implementation ICCV 2021 Mert Bulent Sariyildiz, Yannis Kalantidis, Diane Larlus, Karteek Alahari

In this paper, we argue that the semantic relationships between seen and unseen concepts affect generalization performance and propose ImageNet-CoG, a novel benchmark on the ImageNet-21K (IN-21K) dataset that enables measuring concept generalization in a principled way.

Representation Learning Self-Supervised Learning

Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning

no code implementations CVPR 2021 Riccardo Volpi, Diane Larlus, Grégory Rogez

In this context, we show that one way to learn models that are inherently more robust against forgetting is domain randomization - for vision tasks, randomizing the current domain's distribution with heavy image manipulations.

Meta-Learning Semantic Segmentation

StacMR: Scene-Text Aware Cross-Modal Retrieval

1 code implementation8 Dec 2020 Andrés Mafla, Rafael Sampaio de Rezende, Lluís Gómez, Diane Larlus, Dimosthenis Karatzas

Then, armed with this dataset, we describe several approaches which leverage scene text, including a better scene-text aware cross-modal retrieval method which uses specialized representations for text from the captions and text from the visual scene, and reconcile them in a common embedding space.

Cross-Modal Retrieval Information Retrieval

Hard Negative Mixing for Contrastive Learning

no code implementations NeurIPS 2020 Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel, Diane Larlus

Based on these observations, and motivated by the success of data mixing, we propose hard negative mixing strategies at the feature level, that can be computed on-the-fly with a minimal computational overhead.

Computer Vision Contrastive Learning +6

Learning Visual Representations with Caption Annotations

no code implementations ECCV 2020 Mert Bulent Sariyildiz, Julien Perez, Diane Larlus

Starting from the observation that captioned images are easily crawlable, we argue that this overlooked source of information can be exploited to supervise the training of visual representations.

Computer Vision Image Captioning +2

Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings

no code implementations ICCV 2019 Michael Wray, Diane Larlus, Gabriela Csurka, Dima Damen

We report the first retrieval results on fine-grained actions for the large-scale EPIC dataset, in a generalised zero-shot setting.

Cross-Modal Retrieval POS +2

Re-ID done right: towards good practices for person re-identification

no code implementations16 Jan 2018 Jon Almazan, Bojana Gajic, Naila Murray, Diane Larlus

In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification.

Person Re-Identification

Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval

no code implementations CVPR 2017 Albert Gordo, Diane Larlus

Following this observation, we learn a visual embedding of the images where the similarity in the visual space is correlated with their semantic similarity surrogate.

Image Retrieval Semantic Retrieval +2

Learning 3D Object Categories by Looking Around Them

no code implementations ICCV 2017 David Novotny, Diane Larlus, Andrea Vedaldi

Traditional approaches for learning 3D object categories use either synthetic data or manual supervision.

Data Augmentation

AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching

no code implementations CVPR 2017 David Novotny, Diane Larlus, Andrea Vedaldi

Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG.

End-to-end Learning of Deep Visual Representations for Image Retrieval

4 code implementations25 Oct 2016 Albert Gordo, Jon Almazan, Jerome Revaud, Diane Larlus

Second, we build on the recent R-MAC descriptor, show that it can be interpreted as a deep and differentiable architecture, and present improvements to enhance it.

Computer Vision Image Retrieval +1

Learning the semantic structure of objects from Web supervision

no code implementations5 Jul 2016 David Novotny, Diane Larlus, Andrea Vedaldi

While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important.

What is the right way to represent document images?

no code implementations3 Mar 2016 Gabriela Csurka, Diane Larlus, Albert Gordo, Jon Almazan

In this article we study the problem of document image representation based on visual features.

Understanding the Fisher Vector: a multimodal part model

no code implementations18 Apr 2015 David Novotný, Diane Larlus, Florent Perronnin, Andrea Vedaldi

Fisher Vectors and related orderless visual statistics have demonstrated excellent performance in object detection, sometimes superior to established approaches such as the Deformable Part Models.

object-detection Object Detection

What makes an Image Iconic? A Fine-Grained Case Study

no code implementations19 Aug 2014 Yangmuzi Zhang, Diane Larlus, Florent Perronnin

A natural approach to teaching a visual concept, e. g. a bird species, is to show relevant images.

Incorporating Near-Infrared Information into Semantic Image Segmentation

no code implementations24 Jun 2014 Neda Salamati, Diane Larlus, Gabriela Csurka, Sabine Süsstrunk

Based on a state-of-the-art segmentation framework and a novel manually segmented image database (both indoor and outdoor scenes) that contain 4-channel images (RGB+NIR), we study how to best incorporate the specific characteristics of the NIR response.

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.