Search Results for author:
Found 41 papers, 26 papers with code
DeDrift: Robust Similarity Search under Content Drift
We investigate the impact of this "content drift" for large-scale similarity search tools, based on nearest neighbor search in embedding space.
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").
The Stable Signature: Rooting Watermarks in Latent Diffusion Models
For instance, it detects the origin of an image generated from a text prompt, then cropped to keep $10\%$ of the content, with $90$+$\%$ accuracy at a false positive rate below 10$^{-6}$.
Active Image Indexing
First, a neural network maps an image to a vector representation, that is relatively robust to various transformations of the image.
Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
The outcome of the competition was ranked leaderboards of algorithms in each track based on recall at a query throughput threshold.
A Self-Supervised Descriptor for Image Copy Detection
We adapt this method to the copy detection task by changing the architecture and training objective, including a pooling operator from the instance matching literature, and adapting contrastive learning to augmentations that combine images.
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.
Nearest neighbor search with compact codes: A decoder perspective
Modern approaches for fast retrieval of similar vectors on billion-scaled datasets rely on compressed-domain approaches such as binary sketches or product quantization.
Watermarking Images in Self-Supervised Latent Spaces
We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches.
Embedding Arithmetic of Multimodal Queries for Image Retrieval
We introduce the SIMAT dataset to evaluate the task of Image Retrieval with Multimodal queries.
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
XCiT: Cross-Covariance Image Transformers
We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries.
Ranked #54 on
Instance Segmentation
on COCO minival
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime.
Ranked #11 on
Image Classification
on iNaturalist 2019
Training data-efficient image transformers & distillation through attention
In this work, we produce a competitive convolution-free transformer by training on Imagenet only.
Ranked #8 on
Document Layout Analysis
on PubLayNet val
Grafit: Learning fine-grained image representations with coarse labels
By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods.
Ranked #2 on
Learning with coarse labels
on ImageNet32
Fine-Grained Image Classification
Learning with coarse labels
+3
Powers of layers for image-to-image translation
We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc.
Ranked #1 on
Image-to-Image Translation
on horse2zebra
(Frechet Inception Distance metric)
Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation
Few-shot learning aims to recognize novel classes from a few examples.
Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
Contrastive Predictive Coding (CPC), based on predicting future segments of speech based on past segments is emerging as a powerful algorithm for representation learning of speech signal.
Fixing the train-test resolution discrepancy: FixEfficientNet
An EfficientNet-L2 pre-trained with weak supervision on 300M unlabeled images and further optimized with FixRes achieves 88. 5% top-1 accuracy (top-5: 98. 7%), which establishes the new state of the art for ImageNet with a single crop.
Ranked #8 on
Image Classification
on ImageNet ReaL
(using extra training data)
Radioactive data: tracing through training
The mark is robust to strong variations such as different architectures or optimization methods.
Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition
The transcriptions used to train an Automatic Speech Recognition (ASR) system may contain errors.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set.
Fixing the train-test resolution discrepancy
Conversely, when training a ResNeXt-101 32x48d pre-trained in weakly-supervised fashion on 940 million public images at resolution 224x224 and further optimizing for test resolution 320x320, we obtain a test top-1 accuracy of 86. 4% (top-5: 98. 0%) (single-crop).
Ranked #2 on
Fine-Grained Image Classification
on Birdsnap
(using extra training data)
MultiGrain: a unified image embedding for classes and instances
When fed to a linear classifier, the learned embeddings provide state-of-the-art classification accuracy.
Ranked #1 on
Image Retrieval
on INRIA Holidays
Déjà Vu: an empirical evaluation of the memorization properties of ConvNets
Convolutional neural networks memorize part of their training data, which is why strategies such as data augmentation and drop-out are employed to mitigate overfitting.
Deep Clustering for Unsupervised Learning of Visual Features
In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features.
Ranked #1 on
Image Clustering
on CIFAR-100
(Train Set metric, using extra
training data)
Spreading vectors for similarity search
Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods.
LAMV: Learning to Align and Match Videos With Kernelized Temporal Layers
This paper considers a learnable approach for comparing and aligning videos.
Ranked #4 on
Video Retrieval
on FIVR-200K
Link and code: Fast indexing with graphs and compact regression codes
Similarity search approaches based on graph walks have recently attained outstanding speed-accuracy trade-offs, taking aside the memory requirements.
An evaluation of large-scale methods for image instance and class discovery
While k-means is usually considered as the gold standard for this task, we evaluate and show the interest of diffusion methods that have been neglected by the state of the art, such as the Markov Clustering algorithm.
Low-shot learning with large-scale diffusion
This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time.
Learning Joint Multilingual Sentence Representations with Neural Machine Translation
In this paper, we use the framework of neural machine translation to learn joint sentence representations across six very different languages.
Joint Multilingual Sentence Representations
Machine Translation
+1
Billion-scale similarity search with GPUs
Similarity search finds application in specialized database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures.
FastText.zip: Compressing text classification models
We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory.
How should we evaluate supervised hashing?
Hashing produces compact representations for documents, to perform tasks like classification or retrieval based on these short codes.
Polysemous codes
This paper considers the problem of approximate nearest neighbor search in the compressed domain.
Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach
Convolutional neural networks (CNNs) have recently received a lot of attention due to their ability to model local stationary structures in natural images in a multi-scale fashion, when learning all model parameters with supervision.
Local Convolutional Features With Unsupervised Training for Image Retrieval
Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval.
Beat-Event Detection in Action Movie Franchises
While important advances were recently made towards temporally localizing and recognizing specific human actions or activities in videos, efficient detection and classification of long video chunks belonging to semantically defined categories such as "pursuit" or "romance" remains challenging. We introduce a new dataset, Action Movie Franchises, consisting of a collection of Hollywood action movie franchises.
Circulant temporal encoding for video retrieval and temporal alignment
We address the problem of specific video event retrieval.
Event Retrieval in Large Video Collections with Circulant Temporal Encoding
Furthermore, we extend product quantization to complex vectors in order to compress our descriptors, and to compare them in the compressed domain.
