Gabriela Csurka

Gabriele Berton, Riccardo Mereu, Gabriele Trivigno et al.

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. Code and trained models are available at https://deep-vg-bench.herokuapp.com/.

Martin Humenberger, Yohann Cabon, Noé Pion et al.

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two purposes: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for both of them. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes which often differs from the requirements of visual localization. In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms. First, we introduce a novel benchmark setup and compare state-of-the-art retrieval representations on multiple datasets using localization performance as metric. Second, we investigate several definitions of "ground truth" for image retrieval. Using these definitions as upper bounds for the visual localization paradigms, we show that there is still sgnificant room for improvement. Third, using these tools and in-depth analysis, we show that retrieval performance on classical landmark retrieval or place recognition tasks correlates only for some but not all paradigms to localization performance. Finally, we analyze the effects of blur and dynamic scenes in the images. We conclude that there is a need for retrieval approaches specifically designed for localization paradigms. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.

Philippe Weinzaepfel, Thomas Lucas, Vincent Leroy et al.

Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow. The application of self-supervised concepts, such as instance discrimination or masked image modeling, to geometric tasks is an active area of research. In this work, we build on the recent cross-view completion framework, a variation of masked image modeling that leverages a second view from the same scene which makes it well suited for binocular downstream tasks. The applicability of this concept has so far been limited in at least two ways: (a) by the difficulty of collecting real-world image pairs -- in practice only synthetic data have been used -- and (b) by the lack of generalization of vanilla transformers to dense downstream tasks for which relative position is more meaningful than absolute position. We explore three avenues of improvement. First, we introduce a method to collect suitable real-world image pairs at large scale. Second, we experiment with relative positional embeddings and show that they enable vision transformers to perform substantially better. Third, we scale up vision transformer based cross-completion architectures, which is made possible by the use of large amounts of data. With these improvements, we show for the first time that state-of-the-art results on stereo matching and optical flow can be reached without using any classical task-specific techniques like correlation volume, iterative estimation, image warping or multi-scale reasoning, thus paving the way towards universal vision models.

Ginger Delmas, Rafael Sampaio de Rezende, Gabriela Csurka et al.

An intuitive way to search for images is to use queries composed of an example image and a complementary text. 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. Current approaches typically combine the features of each of the two elements of the query into a single representation, which can then be compared to the ones of the potential target images. Our work aims at shedding new light on the task by looking at it through the prism of two familiar and related frameworks: text-to-image and image-to-image retrieval. Taking inspiration from them, we exploit the specific relation of each query element with the targeted image and derive light-weight attention mechanisms which enable to mediate between the two complementary modalities. We validate our approach on several retrieval benchmarks, querying with images and their associated free-form text modifiers. Our method obtains state-of-the-art results without resorting to side information, multi-level features, heavy pre-training nor large architectures as in previous works.

Philippe Weinzaepfel, Vincent Leroy, Thomas Lucas et al.

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible patches as sole input. This pre-training leads to state-of-the-art performance when finetuned for high-level semantic tasks, e.g. image classification and object detection. In this paper we instead seek to learn representations that transfer well to a wide variety of 3D vision and lower-level geometric downstream tasks, such as depth prediction or optical flow estimation. Inspired by MIM, we propose an unsupervised representation learning task trained from pairs of images showing the same scene from different viewpoints. More precisely, we propose the pretext task of cross-view completion where the first input image is partially masked, and this masked content has to be reconstructed from the visible content and the second image. In single-view MIM, the masked content often cannot be inferred precisely from the visible portion only, so the model learns to act as a prior influenced by high-level semantics. In contrast, this ambiguity can be resolved with cross-view completion from the second unmasked image, on the condition that the model is able to understand the spatial relationship between the two images. Our experiments show that our pretext task leads to significantly improved performance for monocular 3D vision downstream tasks such as depth estimation. In addition, our model can be directly applied to binocular downstream tasks like optical flow or relative camera pose estimation, for which we obtain competitive results without bells and whistles, i.e., using a generic architecture without any task-specific design.

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii

Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two decades of research in the field of SiS, where we propose a literature review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We complement the review by discussing particular cases of the weak supervision and side machine learning techniques that can be used to improve the semantic segmentation such as curriculum, incremental or self-supervised learning. State-of-the-art SiS models rely on a large amount of annotated samples, which are more expensive to obtain than labels for tasks such as image classification. Since unlabeled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation (UDA) reached a broad success within the semantic segmentation community. Therefore, a second core contribution of this book is to summarize five years of a rapidly growing field, Domain Adaptation for Semantic Image Segmentation (DASiS) which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. In addition to providing a comprehensive survey on DASiS techniques, we unveil also newer trends such as multi-domain learning, domain generalization, domain incremental learning, test-time adaptation and source-free domain adaptation. Finally, we conclude this survey by describing datasets and benchmarks most widely used in SiS and DASiS and briefly discuss related tasks such as instance and panoptic image segmentation, as well as applications such as medical image segmentation.

Gabriela Csurka, Tyler L. Hayes, Diane Larlus et al.

Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to be hard to predict when confronted with out-of-distribution samples. In this work, our goal is to propose a simple yet effective solution to predict and describe via natural language potential failure modes of computer vision models. Given a pretrained model and a set of samples, our aim is to find sentences that accurately describe the visual conditions in which the model underperforms. In order to study this important topic and foster future research on it, we formalize the problem of Language-Based Error Explainability (LBEE) and propose a set of metrics to evaluate and compare different methods for this task. We propose solutions that operate in a joint vision-and-language embedding space, and can characterize through language descriptions model failures caused, e.g., by objects unseen during training or adverse visual conditions. We experiment with different tasks, such as classification under the presence of dataset bias and semantic segmentation in unseen environments, and show that the proposed methodology isolates nontrivial sentences associated with specific error causes. We hope our work will help practitioners better understand the behavior of models, increasing their overall safety and interpretability.

Mingxuan Liu, Tyler L. Hayes, Elisa Ricci et al.

Open-vocabulary object detection (OvOD) has transformed detection into a language-guided task, empowering users to freely define their class vocabularies of interest during inference. However, our initial investigation indicates that existing OvOD detectors exhibit significant variability when dealing with vocabularies across various semantic granularities, posing a concern for real-world deployment. To this end, we introduce Semantic Hierarchy Nexus (SHiNe), a novel classifier that uses semantic knowledge from class hierarchies. It runs offline in three steps: i) it retrieves relevant super-/sub-categories from a hierarchy for each target class; ii) it integrates these categories into hierarchy-aware sentences; iii) it fuses these sentence embeddings to generate the nexus classifier vector. Our evaluation on various detection benchmarks demonstrates that SHiNe enhances robustness across diverse vocabulary granularities, achieving up to +31.9% mAP50 with ground truth hierarchies, while retaining improvements using hierarchies generated by large language models. Moreover, when applied to open-vocabulary classification on ImageNet-1k, SHiNe improves the CLIP zero-shot baseline by +2.8% accuracy. SHiNe is training-free and can be seamlessly integrated with any off-the-shelf OvOD detector, without incurring additional computational overhead during inference. The code is open source.

Mingxuan Liu, Tyler L. Hayes, Massimiliano Mancini et al.

Open-vocabulary object detection models allow users to freely specify a class vocabulary in natural language at test time, guiding the detection of desired objects. However, vocabularies can be overly broad or even mis-specified, hampering the overall performance of the detector. In this work, we propose a plug-and-play Vocabulary Adapter (VocAda) to refine the user-defined vocabulary, automatically tailoring it to categories that are relevant for a given image. VocAda does not require any training, it operates at inference time in three steps: i) it uses an image captionner to describe visible objects, ii) it parses nouns from those captions, and iii) it selects relevant classes from the user-defined vocabulary, discarding irrelevant ones. Experiments on COCO and Objects365 with three state-of-the-art detectors show that VocAda consistently improves performance, proving its versatility. The code is open source.

Noé Pion, Martin Humenberger, Gabriela Csurka et al.

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two tasks: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for these tasks. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes. However, robustness to viewpoint changes is not necessarily desirable in the context of visual localization. This paper focuses on understanding the role of image retrieval for multiple visual localization tasks. We introduce a benchmark setup and compare state-of-the-art retrieval representations on multiple datasets. We show that retrieval performance on classical landmark retrieval/recognition tasks correlates only for some but not all tasks to localization performance. This indicates a need for retrieval approaches specifically designed for localization tasks. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.

Martin Humenberger, Yohann Cabon, Nicolas Guerin et al.

Visual localization tackles the challenge of estimating the camera pose from images by using correspondence analysis between query images and a map. This task is computation and data intensive which poses challenges on thorough evaluation of methods on various datasets. However, in order to further advance in the field, we claim that robust visual localization algorithms should be evaluated on multiple datasets covering a broad domain variety. To facilitate this, we introduce kapture, a new, flexible, unified data format and toolbox for visual localization and structure-from-motion (SFM). It enables easy usage of different datasets as well as efficient and reusable data processing. To demonstrate this, we present a versatile pipeline for visual localization that facilitates the use of different local and global features, 3D data (e.g. depth maps), non-vision sensor data (e.g. IMU, GPS, WiFi), and various processing algorithms. Using multiple configurations of the pipeline, we show the great versatility of kapture in our experiments. Furthermore, we evaluate our methods on eight public datasets where they rank top on all and first on many of them. To foster future research, we release code, models, and all datasets used in this paper in the kapture format open source under a permissive BSD license. github.com/naver/kapture, github.com/naver/kapture-localization

Yohann Cabon, Lucas Stoffl, Leonid Antsfeld et al.

DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor viewpoint poses. Under the hood, however, DUSt3R processes image pairs, regressing local 3D reconstructions that need to be aligned in a global coordinate system. The number of pairs, growing quadratically, is an inherent limitation that becomes especially concerning for robust and fast optimization in the case of large image collections. In this paper, we propose an extension of DUSt3R from pairs to multiple views, that addresses all aforementioned concerns. Indeed, we propose a Multi-view Network for Stereo 3D Reconstruction, or MUSt3R, that modifies the DUSt3R architecture by making it symmetric and extending it to directly predict 3D structure for all views in a common coordinate frame. Second, we entail the model with a multi-layer memory mechanism which allows to reduce the computational complexity and to scale the reconstruction to large collections, inferring thousands of 3D pointmaps at high frame-rates with limited added complexity. The framework is designed to perform 3D reconstruction both offline and online, and hence can be seamlessly applied to SfM and visual SLAM scenarios showing state-of-the-art performance on various 3D downstream tasks, including uncalibrated Visual Odometry, relative camera pose, scale and focal estimation, 3D reconstruction and multi-view depth estimation.

Lojze Zust, Yohann Cabon, Juliette Marrie et al.

Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing approaches typically leverage off-the-shelf models to extract per-frame 2D panoptic segmentations, before optimizing an implicit geometric representation (often based on NeRF) to integrate and fuse the 2D predictions. We argue that relying on 2D panoptic segmentation for a problem inherently 3D and multi-view is likely suboptimal as it fails to leverage the full potential of spatial relationships across views. In addition to requiring camera parameters, these approaches also necessitate computationally expensive test-time optimization for each scene. Instead, in this work, we propose a unified and integrated approach PanSt3R, which eliminates the need for test-time optimization by jointly predicting 3D geometry and multi-view panoptic segmentation in a single forward pass. Our approach builds upon recent advances in 3D reconstruction, specifically upon MUSt3R, a scalable multi-view version of DUSt3R, and enhances it with semantic awareness and multi-view panoptic segmentation capabilities. We additionally revisit the standard post-processing mask merging procedure and introduce a more principled approach for multi-view segmentation. We also introduce a simple method for generating novel-view predictions based on the predictions of PanSt3R and vanilla 3DGS. Overall, the proposed PanSt3R is conceptually simple, yet fast and scalable, and achieves state-of-the-art performance on several benchmarks, while being orders of magnitude faster than existing methods.

Maxime Pietrantoni, Gabriela Csurka, Torsten Sattler

Visual localization is the task of estimating a camera pose in a known environment. In this paper, we utilize 3D Gaussian Splatting (3DGS)-based representations for accurate and privacy-preserving visual localization. We propose Gaussian Splatting Feature Fields (GSFFs), a scene representation for visual localization that combines an explicit geometry model (3DGS) with an implicit feature field. We leverage the dense geometric information and differentiable rasterization algorithm from 3DGS to learn robust feature representations grounded in 3D. In particular, we align a 3D scale-aware feature field and a 2D feature encoder in a common embedding space through a contrastive framework. Using a 3D structure-informed clustering procedure, we further regularize the representation learning and seamlessly convert the features to segmentations, which can be used for privacy-preserving visual localization. Pose refinement, which involves aligning either feature maps or segmentations from a query image with those rendered from the GSFFs scene representation, is used to achieve localization. The resulting privacy- and non-privacy-preserving localization pipelines, evaluated on multiple real-world datasets, show state-of-the-art performances.

Maxime Pietrantoni, Martin Humenberger, Torsten Sattler et al.

Visual localization (VL) is the task of estimating the camera pose in a known scene. VL methods, a.o., can be distinguished based on how they represent the scene, e.g., explicitly through a (sparse) point cloud or a collection of images or implicitly through the weights of a neural network. Recently, NeRF-based methods have become popular for VL. While NeRFs offer high-quality novel view synthesis, they inadvertently encode fine scene details, raising privacy concerns when deployed in cloud-based localization services as sensitive information could be recovered. In this paper, we tackle this challenge on two ends. We first propose a new protocol to assess privacy-preservation of NeRF-based representations. We show that NeRFs trained with photometric losses store fine-grained details in their geometry representations, making them vulnerable to privacy attacks, even if the head that predicts colors is removed. Second, we propose ppNeSF (Privacy-Preserving Neural Segmentation Field), a NeRF variant trained with segmentation supervision instead of RGB images. These segmentation labels are learned in a self-supervised manner, ensuring they are coarse enough to obscure identifiable scene details while remaining discriminativeness in 3D. The segmentation space of ppNeSF can be used for accurate visual localization, yielding state-of-the-art results.

Gianluca Monaci, Rafael S. Rezende, Romain Deffayet et al.

Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While these generalization capabilities to an unknown environment are extremely important, we claim that, in a realistic setting, an agent should have the capacity of exploiting information collected during earlier robot operations. We address this by introducing a new retrieval-augmented agent, trained with RL, capable of querying a database collected from previous episodes in the same environment and learning how to integrate this additional context information. We introduce a unique agent architecture for the general navigation task, evaluated on ImageNav, Instance-ImageNav and ObjectNav. Our retrieval and context encoding methods are data-driven and employ vision foundation models (FM) for both semantic and geometric understanding. We propose new benchmarks for these settings and we show that retrieval allows zero-shot transfer across tasks and environments while significantly improving performance.

Maxime Pietrantoni, Gabriela Csurka, Martin Humenberger et al.

Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former requires sparse feature extractors and matchers to build the scene representation. The latter might lack geometric grounding not capturing the 3D structure of the scene well enough. This paper proposes to jointly learn the scene representation along with a 3D dense feature field and a 2D feature extractor whose outputs are embedded in the same metric space. Through a contrastive framework we align this volumetric field with the image-based extractor and regularize the latter with a ranking loss from learned surface information. We learn the underlying geometry of the scene with an implicit field through volumetric rendering and design our feature field to leverage intermediate geometric information encoded in the implicit field. The resulting features are discriminative and robust to viewpoint change while maintaining rich encoded information. Visual localization is then achieved by aligning the image-based features and the rendered volumetric features. We show the effectiveness of our approach on real-world scenes, demonstrating that our approach outperforms prior and concurrent work on leveraging implicit scene representations for localization.

Yannis Kalantidis, Mert Bülent Sarıyıldız, Rafael S. Rezende et al.

State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions, due to e.g. weather or time of day, with dramatic consequences on the visual localization accuracy. In this paper, we improve this retrieval step and tailor it to the final localization task. Among the several changes we advocate for, we propose to synthesize variants of the training set images, obtained from generative text-to-image models, in order to automatically expand the training set towards a number of nameable variations that particularly hurt visual localization. After expanding the training set, we propose a training approach that leverages the specificities and the underlying geometry of this mix of real and synthetic images. We experimentally show that those changes translate into large improvements for the most challenging visual localization datasets. Project page: https://europe.naverlabs.com/ret4loc

Subhankar Roy, Riccardo Volpi, Gabriela Csurka et al.

Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories. This is typically carried out by providing expensive pixel-level annotations to the training algorithm for all new objects, limiting the adoption of such methods in practical applications. Approaches that solely require image-level labels offer an attractive alternative, yet, such coarse annotations lack precise information about the location and boundary of the new objects. In this paper we argue that, since classes represent not just indices but semantic entities, the conceptual relationships between them can provide valuable information that should be leveraged. We propose a weakly supervised approach that exploits such semantic relations to transfer objectness prior from the previously learned classes into the new ones, complementing the supervisory signal from image-level labels. We validate our approach on a number of continual learning tasks, and show how even a simple pairwise interaction between classes can significantly improve the segmentation mask quality of both old and new classes. We show these conclusions still hold for longer and, hence, more realistic sequences of tasks and for a challenging few-shot scenario.

Riccardo Volpi, Pau de Jorge, Diane Larlus et al.

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.

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii

Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. Yet, the state-of-the-art models rely on large amount of annotated samples, which are more expensive to obtain than in tasks such as image classification. Since unlabelled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation reached a broad success within the semantic segmentation community. This survey is an effort to summarize five years of this incredibly rapidly growing field, which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. We present the most important semantic segmentation methods; we provide a comprehensive survey on domain adaptation techniques for semantic segmentation; we unveil newer trends such as multi-domain learning, domain generalization, test-time adaptation or source-free domain adaptation; we conclude this survey by describing datasets and benchmarks most widely used in semantic segmentation research. We hope that this survey will provide researchers across academia and industry with a comprehensive reference guide and will help them in fostering new research directions in the field.

Jonathan Munro, Michael Wray, Diane Larlus et al.

Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving videos based on their relevance to an unseen text query. To compensate for the lack of annotations, we rely instead on a related video gallery composed of video-caption pairs, termed the source gallery, albeit with a domain gap between its videos and those in the target gallery. We thus introduce the problem of Unsupervised Domain Adaptation for Cross-modal Video Retrieval, along with a new benchmark on fine-grained actions. We propose a novel iterative domain alignment method by means of pseudo-labelling target videos and cross-domain (i.e. source-target) ranking. Our approach adapts the embedding space to the target gallery, consistently outperforming source-only as well as marginal and conditional alignment methods.

Donghwan Lee, Soohyun Ryu, Suyong Yeon et al.

Estimating the precise location of a camera using visual localization enables interesting applications such as augmented reality or robot navigation. This is particularly useful in indoor environments where other localization technologies, such as GNSS, fail. Indoor spaces impose interesting challenges on visual localization algorithms: occlusions due to people, textureless surfaces, large viewpoint changes, low light, repetitive textures, etc. Existing indoor datasets are either comparably small or do only cover a subset of the mentioned challenges. In this paper, we introduce 5 new indoor datasets for visual localization in challenging real-world environments. They were captured in a large shopping mall and a large metro station in Seoul, South Korea, using a dedicated mapping platform consisting of 10 cameras and 2 laser scanners. In order to obtain accurate ground truth camera poses, we developed a robust LiDAR SLAM which provides initial poses that are then refined using a novel structure-from-motion based optimization. We present a benchmark of modern visual localization algorithms on these challenging datasets showing superior performance of structure-based methods using robust image features. The datasets are available at: https://naverlabs.com/datasets

Gabriela Csurka

Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data hungry, the interest for visual DA has significantly increased in the last decade and the number of related work in the field exploded. The aim of this paper, therefore, is to give a comprehensive overview of deep domain adaptation methods for computer vision applications. First, we detail and compared different possible ways of exploiting deep architectures for domain adaptation. Then, we propose an overview of recent trends in deep visual DA. Finally, we mention a few improvement strategies, orthogonal to these methods, that can be applied to these models. While we mainly focus on image classification, we give pointers to papers that extend these ideas for other applications such as semantic segmentation, object detection, person re-identifications, and others.

Michael Wray, Diane Larlus, Gabriela Csurka et al.

We address the problem of cross-modal fine-grained action retrieval between text and video. Cross-modal retrieval is commonly achieved through learning a shared embedding space, that can indifferently embed modalities. In this paper, we propose to enrich the embedding by disentangling parts-of-speech (PoS) in the accompanying captions. We build a separate multi-modal embedding space for each PoS tag. The outputs of multiple PoS embeddings are then used as input to an integrated multi-modal space, where we perform action retrieval. All embeddings are trained jointly through a combination of PoS-aware and PoS-agnostic losses. Our proposal enables learning specialised embedding spaces that offer multiple views of the same embedded entities. We report the first retrieval results on fine-grained actions for the large-scale EPIC dataset, in a generalised zero-shot setting. Results show the advantage of our approach for both video-to-text and text-to-video action retrieval. We also demonstrate the benefit of disentangling the PoS for the generic task of cross-modal video retrieval on the MSR-VTT dataset.

Jerome Revaud, Philippe Weinzaepfel, César De Souza et al.

Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical methods for these tasks are based on a detect-then-describe paradigm where separate handcrafted methods are used to first identify repeatable keypoints and then represent them with a local descriptor. Neural networks trained with metric learning losses have recently caught up with these techniques, focusing on learning repeatable saliency maps for keypoint detection and learning descriptors at the detected keypoint locations. In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description. Furthermore, we claim that descriptors should be learned only in regions for which matching can be performed with high confidence. We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness. This allows us to avoid ambiguous areas and leads to reliable keypoint detections and descriptions. Our detection-and-description approach, trained with self-supervision, can simultaneously output sparse, repeatable and reliable keypoints that outperforms state-of-the-art detectors and descriptors on the HPatches dataset. It also establishes a record on the recently released Aachen Day-Night localization dataset.

Gabriela Csurka, Christopher R. Dance, Martin Humenberger

This paper presents an overview of the evolution of local features from handcrafted to deep-learning-based methods, followed by a discussion of several benchmarks and papers evaluating such local features. Our investigations are motivated by 3D reconstruction problems, where the precise location of the features is important. As we describe these methods, we highlight and explain the challenges of feature extraction and potential ways to overcome them. We first present handcrafted methods, followed by methods based on classical machine learning and finally we discuss methods based on deep-learning. This largely chronologically-ordered presentation will help the reader to fully understand the topic of image and region description in order to make best use of it in modern computer vision applications. In particular, understanding handcrafted methods and their motivation can help to understand modern approaches and how machine learning is used to improve the results. We also provide references to most of the relevant literature and code.

Gabriela Csurka, Boris Chidlovski, Stephane Clinchant et al.

We propose an extended framework for marginalized domain adaptation, aimed at addressing unsupervised, supervised and semi-supervised scenarios. We argue that the denoising principle should be extended to explicitly promote domain-invariant features as well as help the classification task. Therefore we propose to jointly learn the data auto-encoders and the target classifiers. First, in order to make the denoised features domain-invariant, we propose a domain regularization that may be either a domain prediction loss or a maximum mean discrepancy between the source and target data. The noise marginalization in this case is reduced to solving the linear matrix system $AX=B$ which has a closed-form solution. Second, in order to help the classification, we include a class regularization term. Adding this component reduces the learning problem to solving a Sylvester linear matrix equation $AX+BX=C$, for which an efficient iterative procedure exists as well. We did an extensive study to assess how these regularization terms improve the baseline performance in the three domain adaptation scenarios and present experimental results on two image and one text benchmark datasets, conventionally used for validating domain adaptation methods. We report our findings and comparison with state-of-the-art methods.

Gabriela Csurka

The aim of this paper is to give an overview of domain adaptation and transfer learning with a specific view on visual applications. After a general motivation, we first position domain adaptation in the larger transfer learning problem. Second, we try to address and analyze briefly the state-of-the-art methods for different types of scenarios, first describing the historical shallow methods, addressing both the homogeneous and the heterogeneous domain adaptation methods. Third, we discuss the effect of the success of deep convolutional architectures which led to new type of domain adaptation methods that integrate the adaptation within the deep architecture. Fourth, we overview the methods that go beyond image categorization, such as object detection or image segmentation, video analyses or learning visual attributes. Finally, we conclude the paper with a section where we relate domain adaptation to other machine learning solutions.

Gabriela Csurka, Diane Larlus, Albert Gordo et al.

In this article we study the problem of document image representation based on visual features. We propose a comprehensive experimental study that compares three types of visual document image representations: (1) traditional so-called shallow features, such as the RunLength and the Fisher-Vector descriptors, (2) deep features based on Convolutional Neural Networks, and (3) features extracted from hybrid architectures that take inspiration from the two previous ones. We evaluate these features in several tasks (i.e. classification, clustering, and retrieval) and in different setups (e.g. domain transfer) using several public and in-house datasets. Our results show that deep features generally outperform other types of features when there is no domain shift and the new task is closely related to the one used to train the model. However, when a large domain or task shift is present, the Fisher-Vector shallow features generalize better and often obtain the best results.

Gabriela Csurka

The main focus of this paper is document image classification and retrieval, where we analyze and compare different parameters for the RunLeght Histogram (RL) and Fisher Vector (FV) based image representations. We do an exhaustive experimental study using different document image datasets, including the MARG benchmarks, two datasets built on customer data and the images from the Patent Image Classification task of the Clef-IP 2011. The aim of the study is to give guidelines on how to best choose the parameters such that the same features perform well on different tasks. As an example of such need, we describe the Image-based Patent Retrieval task's of Clef-IP 2011, where we used the same image representation to predict the image type and retrieve relevant patents.

Neda Salamati, Diane Larlus, Gabriela Csurka et al.

Recent progress in computational photography has shown that we can acquire near-infrared (NIR) information in addition to the normal visible (RGB) band, with only slight modifications to standard digital cameras. Due to the proximity of the NIR band to visible radiation, NIR images share many properties with visible images. However, as a result of the material dependent reflection in the NIR part of the spectrum, such images reveal different characteristics of the scene. We investigate how to effectively exploit these differences to improve performance on the semantic image segmentation task. 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. We show that adding NIR leads to improved performance for classes that correspond to a specific type of material in both outdoor and indoor scenes. We also discuss the results with respect to the physical properties of the NIR response.

Gabriela Csurka, Julien Ah-Pine, Stéphane Clinchant

Multimedia collections are more than ever growing in size and diversity. Effective multimedia retrieval systems are thus critical to access these datasets from the end-user perspective and in a scalable way. We are interested in repositories of image/text multimedia objects and we study multimodal information fusion techniques in the context of content based multimedia information retrieval. We focus on graph based methods which have proven to provide state-of-the-art performances. We particularly examine two of such methods : cross-media similarities and random walk based scores. From a theoretical viewpoint, we propose a unifying graph based framework which encompasses the two aforementioned approaches. Our proposal allows us to highlight the core features one should consider when using a graph based technique for the combination of visual and textual information. We compare cross-media and random walk based results using three different real-world datasets. From a practical standpoint, our extended empirical analysis allow us to provide insights and guidelines about the use of graph based methods for multimodal information fusion in content based multimedia information retrieval.