• Publications
  • Influence
Aggregating local descriptors into a compact image representation
This work proposes a simple yet efficient way of aggregating local image descriptors into a vector of limited dimension, which can be viewed as a simplification of the Fisher kernel representation, and shows how to jointly optimize the dimension reduction and the indexing algorithm. Expand
Product Quantization for Nearest Neighbor Search
This paper introduces a product quantization-based approach for approximate nearest neighbor search. The idea is to decompose the space into a Cartesian product of low-dimensional subspaces and toExpand
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search
Estimation of the full geometric transformation of bag-of-features in the framework of approximate nearest neighbor search is complementary to the weak geometric consistency constraints and allows to further improve the accuracy. Expand
Aggregating Local Image Descriptors into Compact Codes
This paper first presents and evaluates different ways of aggregating local image descriptors into a vector and shows that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. Expand
Training data-efficient image transformers & distillation through attention
This work produces a competitive convolution-free transformer by training on Imagenet only, and introduces a teacher-student strategy specific to transformers that relies on a distillation token ensuring that the student learns from the teacher through attention. Expand
Deep Clustering for Unsupervised Learning of Visual Features
This work presents DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features and outperforms the current state of the art by a significant margin on all the standard benchmarks. Expand
Billion-Scale Similarity Search with GPUs
This paper proposes a novel design for an inline-formula that enables the construction of a high accuracy, brute-force, approximate and compressed-domain search based on product quantization, and applies it in different similarity search scenarios. Expand
Improving Bag-of-Features for Large Scale Image Search
A more precise representation based on Hamming embedding (HE) and weak geometric consistency constraints (WGC) is derived and this approach is shown to outperform the state-of-the-art on the three datasets. Expand
FastText.zip: Compressing text classification models
This work proposes a method built upon product quantization to store the word embeddings, which produces a text classifier, derived from the fastText approach, which at test time requires only a fraction of the memory compared to the original one, without noticeably sacrificing the quality in terms of classification accuracy. Expand
Searching in one billion vectors: Re-rank with source coding
This paper releases a new public dataset of one billion 128-dimensional vectors and proposed an experimental setup to evaluate high dimensional indexing algorithms on a realistic scale and accurately and efficiently re-ranks the neighbor hypotheses using little memory compared to the full vectors representation. Expand