Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search

By Herv'e J'egou, Matthijs Douze, Cordelia Schmid. 2008

2,098 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Information Retrieval & Search

Citations in the corpus

Aggregating Local Image Descriptors into Compact Codes (2012, methodology): “The INRIA Holidays dataset [26] is a collection of 1491 holiday images, 500 of them being used as queries.”
Product Quantization for Nearest Neighbor Search (2011, methodology): “Comparison with Hamming embedding methods: We compare our approach to spectral hashing (SH) [19], which maps vectors to binary signatures.”
Unbounded cache model for online language modeling with open vocabulary (2017, methodology): “In this section, we brieﬂy describe a scalable retrieval method introduced by Jegou et al. [27].”
Revisiting IM2GPS in the Deep Learning Era (2017, background): “…scene retrieval [33, 2, 23, 7]; Since this line of work mostly focuses on instance-level matching, benchmarks designed for this task consist of popular scenes or landmarks [21, 22, 12] and similarity between matched images are visually recognizable (by humans or geometric veriﬁcation).”
PlaNet - Photo Geolocation with Convolutional Neural Networks (2016, methodology): “To test this, we evaluate the PlaNet features on the INRIA Holi-days dataset [23], consisting of 1,491 personal holiday photos, including landmarks, cities and natural scenes.”
FastText.zip: Compressing text classification models (2016, methodology): “Note that we use an improved version of LSH where random orthogonal matrices are used instead of random matrix projection J´egou et al. (2008).”
Compressing Deep Convolutional Networks using Vector Quantization (2014, methodology): “We performed experiments on the Holidays dataset (Jegou et al., 2008).”
Fast ConvNets Using Group-Wise Brain Damage (2015, background): “2x speedup, we have found a negligible drop in performance for the INRIA holidays dataset [23] from 0.”
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition (2015, background): “roves over current state-of-the-art compact image representations on standard image retrieval benchmarks. 1.1. Related work While there have been many improvements in designing better image retrieval [2,3,11,12,17,25,26,27,29, 32,48,51,52,53,54,71,78,79,82] and place recognition [4,9,10,15,16,24,35,”
MultiGrain: a unified image embedding for classes and instances (2019, methodology): ““Image search” is a generic retrieval task that is usually associated with and evaluated for more specific problems such as landmark recognition [25, 33], particular object recognition [31] or copy detection [8], for which the objective is to find the images most similar to the query in a large imag”
Multi-scale Orderless Pooling of Deep Convolutional Activation Features (2014, background): “Section 4 presents experiments results for classification on three image datasets (SUN 397, MIT Indoor, and ILSVRC2012) and retrieval on the Holidays dataset.”
From generic to specific deep representations for visual recognition (2014, background): “PASCAL VOC Object [9] H3D human attributes [6] Cat&Dog breeds [25] VOC Human Action [9] Holiday scenes [16] MIT 67 Indoor Scenes [29] Object attributes [10] Bird subordinate [39] Stanford 40 Actions [42] Paris buildings [27] SUN 397 Scene [41] SUN scene attributes [26] 102 Flowers [23] Visual Phrase”
End-to-End Learning of Deep Visual Representations for Image Retrieval (2016, methodology): “Encoding techniques, such as the Fisher Vector (Perronnin and Dance, 2007; Perronnin et al, 2010) or the VLAD descriptor (Jégou et al, 2010) have been used for example by Perronnin et al (2010); Gordo et al (2012); Jégou and Chum (2012); Radenovic et al (2015).”
Aggregating local descriptors into a compact image representation (2010, background): “VLAD k=16 VLAD k=64 VLAD k=256 miniBOF [8] miniBOF 1 miniBOF 4 miniBOF 8 miniBOF 16 miniBOF 32”
Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost (2013, methodology): “First, the INRIA Holidays data set [48], which consists of 1,491 images of 500 scenes and objects.”
Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval (2013, neutral): “The idea of rotating the data to minimize quantization loss can be found in [17] and [19].”
Locality sensitive hashing: A comparison of hash function types and querying mechanisms (2010, positive): “…functions have recently been proposed to improve the performance of E2LSH, including the Leech lat-tices (Shakhnarovich et al., 2006) and E8 lattices (J´egou et al., 2008a), which o ﬀ er strong quantization properties, and spherical hash functions (Terasawa and Tanaka, 2007) for unit-norm vectors.”