Search Results for author:
Found 42 papers, 27 papers with code
A Dataset for Semantic Segmentation in the Presence of Unknowns
The dataset is twice larger than existing anomaly segmentation datasets, and provides a training, validation and test set for controlled in-domain evaluation.
LOCORE: Image Re-ranking with Long-Context Sequence Modeling
We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity scores between the query and each gallery image.
LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs).
cross-modal alignment
Open Vocabulary Semantic Segmentation
+2
ILIAS: Instance-Level Image retrieval At Scale
An extensive benchmarking is performed with the following observations: i) models fine-tuned on specific domains, such as landmarks or products, excel in that domain but fail on ILIAS ii) learning a linear adaptation layer using multi-domain class supervision results in performance improvements, especially for vision-language models iii) local descriptors in retrieval re-ranking are still a key ingredient, especially in the presence of severe background clutter iv) the text-to-image performance of the vision-language foundation models is surprisingly close to the corresponding image-to-image case.
Three Things to Know about Deep Metric Learning
This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization.
Composed Image Retrieval for Training-Free Domain Conversion
This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text.
Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization
The method that achieves the best performance on the augmented validation is selected from the proposed family.
Ranked #1 on
Single-Source Domain Generalization
on Digits-five
AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval
The proposed model uses a transformer-based architecture designed to estimate image-to-image similarity by capturing interactions within and across images based on their local descriptors.
Composed Image Retrieval for Remote Sensing
Various attributes can be modified by the textual part, such as shape, color, or context.
Label Propagation for Zero-shot Classification with Vision-Language Models
We leverage the graph structure of the unlabeled data and introduce ZLaP, a method based on label propagation (LP) that utilizes geodesic distances for classification.
Ranked #1 on
Zero-Shot Learning
on EuroSAT
Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning
In this work, we present an approach that leverages three highly synergistic components, which are identified as key ingredients: joint classifier training with inliers and outliers, semi-supervised learning through pseudo-labeling, and model ensembling.
The 2023 Video Similarity Dataset and Challenge
The problem comprises two distinct but related tasks: determining whether a query video shares content with a reference video ("detection"), and additionally temporally localizing the shared content within each video ("localization").
HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer
In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image.
Self-Supervised Video Similarity Learning
We introduce S$^2$VS, a video similarity learning approach with self-supervision.
Ranked #1 on
Video Retrieval
on FIVR-200K
Rethinking matching-based few-shot action recognition
Few-shot action recognition, i. e. recognizing new action classes given only a few examples, benefits from incorporating temporal information.
Large-to-small Image Resolution Asymmetry in Deep Metric Learning
The goal is to obtain a network for database examples that is trained to operate on large resolution images and benefits from fine-grained image details, and a second network for query examples that operates on small resolution images but preserves a representation space aligned with that of the database network.
Edge Augmentation for Large-Scale Sketch Recognition without Sketches
To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images.
Ranked #1 on
Image to sketch recognition
on Im4Sketch
Results and findings of the 2021 Image Similarity Challenge
The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods.
The Met Dataset: Instance-level Recognition for Artworks
Testing is primarily performed on photos taken by museum guests depicting exhibits, which introduces a distribution shift between training and testing.
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach.
Ranked #1 on
Vehicle Re-Identification
on VehicleID Small
The 2021 Image Similarity Dataset and Challenge
This benchmark is used for the Image Similarity Challenge at NeurIPS'21 (ISC2021).
Ranked #1 on
Image Similarity Detection
on DISC21 dev
Learning and aggregating deep local descriptors for instance-level recognition
At inference, the local descriptors are provided by the activations of internal components of the network.
Ranked #6 on
Image Retrieval
on ROxford (Medium)
Graph convolutional networks for learning with few clean and many noisy labels
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given.
Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Tower
We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction.
Explicit Spatial Encoding for Deep Local Descriptors
We evaluate the descriptor on standard benchmarks.
Label Propagation for Deep Semi-supervised Learning
In this work, we employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network.
Understanding and Improving Kernel Local Descriptors
We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients.
Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking
State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line.
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth.
Mining on Manifolds: Metric Learning without Labels
Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds.
Fine-tuning CNN Image Retrieval with No Human Annotation
We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval.
Ranked #10 on
Image Retrieval
on RParis (Medium)
Unsupervised object discovery for instance recognition
Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion.
Deep Shape Matching
We cast shape matching as metric learning with convolutional networks.
Ranked #1 on
Sketch-Based Image Retrieval
on Chairs
(using extra training data)
Multiple-Kernel Local-Patch Descriptor
We propose a multiple-kernel local-patch descriptor based on efficient match kernels of patch gradients.
Panorama to panorama matching for location recognition
Location recognition is commonly treated as visual instance retrieval on "street view" imagery.
Asymmetric Feature Maps with Application to Sketch Based Retrieval
To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval.
Fast Spectral Ranking for Similarity Search
This makes the Euclidean nearest neighbor search biased for this task.
Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations
The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches.
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.
Ranked #5 on
Image Retrieval
on Par6k
Particular object retrieval with integral max-pooling of CNN activations
Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations.
Ranked #4 on
Image Retrieval
on Par6k
A comparison of dense region detectors for image search and fine-grained classification
Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks.
Orientation covariant aggregation of local descriptors with embeddings
Our geometric-aware aggregation strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.
