Product Quantization for Nearest Neighbor Search
TLDR
This paper introduces a product quantization-based approach for approximate nearest neighbor search to decompose the space into a Cartesian product of low-dimensional subspaces and to quantize each subspace separately.Abstract:
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 to quantize each subspace separately. A vector is represented by a short code composed of its subspace quantization indices. The euclidean distance between two vectors can be efficiently estimated from their codes. An asymmetric version increases precision, as it computes the approximate distance between a vector and a code. Experimental results show that our approach searches for nearest neighbors efficiently, in particular in combination with an inverted file system. Results for SIFT and GIST image descriptors show excellent search accuracy, outperforming three state-of-the-art approaches. The scalability of our approach is validated on a data set of two billion vectors.read more
Citations
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Proceedings ArticleDOI
Aggregating local descriptors into a compact image representation
TL;DR: 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.
Proceedings Article
FitNets: Hints for Thin Deep Nets
Adriana Romero,Nicolas Ballas,Samira Ebrahimi Kahou,Antoine Chassang,Carlo Gatta,Yoshua Bengio +5 more
TL;DR: This paper extends the idea of a student network that could imitate the soft output of a larger teacher network or ensemble of networks, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student.
Journal Article
When is nearest neighbor meaningful
TL;DR: In this article, the authors explore the effect of dimensionality on the nearest neighbor problem and show that under a broad set of conditions (much broader than independent and identically distributed dimensions), as dimensionality increases, the distance to the nearest data point approaches the distance of the farthest data point.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Proceedings ArticleDOI
Video Google: a text retrieval approach to object matching in videos
TL;DR: An approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video, represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, illumination and partial occlusion.
Journal ArticleDOI
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Aude Oliva,Antonio Torralba +1 more
TL;DR: The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.
Proceedings ArticleDOI
Scalable Recognition with a Vocabulary Tree
David Nister,Henrik Stewenius +1 more
TL;DR: A recognition scheme that scales efficiently to a large number of objects and allows a larger and more discriminatory vocabulary to be used efficiently is presented, which it is shown experimentally leads to a dramatic improvement in retrieval quality.
Proceedings Article
Similarity Search in High Dimensions via Hashing
TL;DR: Experimental results indicate that the novel scheme for approximate similarity search based on hashing scales well even for a relatively large number of dimensions, and provides experimental evidence that the method gives improvement in running time over other methods for searching in highdimensional spaces based on hierarchical tree decomposition.