Search Results for author:
Found 37 papers, 13 papers with code
PANDAS: Prototype-based Novel Class Discovery and Detection
In this work, we look at ways to extend a detector trained for a set of base classes so it can i) spot the presence of novel classes, and ii) automatically enrich its repertoire to be able to detect those newly discovered classes together with the base ones.
On Good Practices for Task-Specific Distillation of Large Pretrained Models
Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks.
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
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.
SLACK: Stable Learning of Augmentations with Cold-start and KL regularization
Data augmentation is known to improve the generalization capabilities of neural networks, provided that the set of transformations is chosen with care, a selection often performed manually.
EPIC Fields: Marrying 3D Geometry and Video Understanding
Compared to other neural rendering datasets, EPIC Fields is better tailored to video understanding because it is paired with labelled action segments and the recent VISOR segment annotations.
RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories.
Fake it till you make it: Learning transferable representations from synthetic ImageNet clones
We show that with minimal and class-agnostic prompt engineering, ImageNet clones are able to close a large part of the gap between models produced by synthetic images and models trained with real images, for the several standard classification benchmarks that we consider in this study.
Granularity-aware Adaptation for Image Retrieval over Multiple Tasks
We address it with the proposed Grappa, an approach that starts from a strong pretrained model, and adapts it to tackle multiple retrieval tasks concurrently, using only unlabeled images from the different task domains.
Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations
We present Neural Feature Fusion Fields (N3F), a method that improves dense 2D image feature extractors when the latter are applied to the analysis of multiple images reconstructible as a 3D scene.
No Reason for No Supervision: Improved Generalization in Supervised Models
We consider the problem of training a deep neural network on a given classification task, e. g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other (future) transfer tasks.
On the Road to Online Adaptation for Semantic Image Segmentation
We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation.
ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity
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.
Ranked #11 on
Image Retrieval
on CIRR
Learning Super-Features for Image Retrieval
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.
Ranked #3 on
Image Retrieval
on ROxford (Medium)
Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval
Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving videos based on their relevance to an unseen text query.
NeuralDiff: Segmenting 3D objects that move in egocentric videos
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.
TLDR: Twin Learning for Dimensionality Reduction
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.
Probabilistic Embeddings for Cross-Modal Retrieval
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.
Concept Generalization in Visual Representation Learning
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.
StacMR: Scene-Text Aware Cross-Modal Retrieval
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.
Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning
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.
Hard Negative Mixing for Contrastive Learning
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.
Learning Visual Representations with Caption Annotations
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.
Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings
We report the first retrieval results on fine-grained actions for the large-scale EPIC dataset, in a generalised zero-shot setting.
Semi-convolutional Operators for Instance Segmentation
Object detection and instance segmentation are dominated by region-based methods such as Mask RCNN.
Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks.
Re-ID done right: towards good practices for person re-identification
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.
Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval
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.
Learning 3D Object Categories by Looking Around Them
Traditional approaches for learning 3D object categories use either synthetic data or manual supervision.
AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching
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
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.
Ranked #13 on
Image Retrieval
on ROxford (Medium)
Learning the semantic structure of objects from Web supervision
While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important.
Deep Image Retrieval: Learning global representations for image search
We propose a novel approach for instance-level image retrieval.
Ranked #3 on
Image Retrieval
on Oxf105k
What is the right way to represent document images?
In this article we study the problem of document image representation based on visual features.
Fisher Vectors Meet Neural Networks: A Hybrid Classification Architecture
Fisher Vectors (FV) and Convolutional Neural Networks(CNN) are two image classification pipelines with different strengths.
Understanding the Fisher Vector: a multimodal part model
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.
What makes an Image Iconic? A Fine-Grained Case Study
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
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.
