arXiv subjects

Teddy Furon

Publications and source records attributed to Teddy Furon.

48 records · Page 3Linked to original sources

arXiv2018

Fast Spectral Ranking for Similarity Search

Despite the success of deep learning on representing images for particular object retrieval, recent studies show that the learned representations still lie on manifolds in a high dimensional space. This makes the Euclidean nearest neighbor search biased for this task. Exploring the manifolds online remains expensive even if a nearest neighbor graph has been computed offline. This work introduces an explicit embedding reducing manifold search to Euclidean search followed by dot product similarity search. This is equivalent to linear graph filtering of a sparse signal in the frequency domain. To speed up online search, we compute an approximate Fourier basis of the graph offline. We improve the state of art on particular object retrieval datasets including the challenging Instre dataset containing small objects. At a scale of 10^5 images, the offline cost is only a few hours, while query time is comparable to standard similarity search.

cs.CV↗

arXiv2017

Panorama to panorama matching for location recognition

Location recognition is commonly treated as visual instance retrieval on "street view" imagery. The dataset items and queries are panoramic views, i.e. groups of images taken at a single location. This work introduces a novel panorama-to-panorama matching process, either by aggregating features of individual images in a group or by explicitly constructing a larger panorama. In either case, multiple views are used as queries. We reach near perfect location recognition on a standard benchmark with only four query views.

cs.CV↗

arXiv2017

Memory vectors for similarity search in high-dimensional spaces

We study an indexing architecture to store and search in a database of high-dimensional vectors from the perspective of statistical signal processing and decision theory. This architecture is composed of several memory units, each of which summarizes a fraction of the database by a single representative vector. The potential similarity of the query to one of the vectors stored in the memory unit is gauged by a simple correlation with the memory unit's representative vector. This representative optimizes the test of the following hypothesis: the query is independent from any vector in the memory unit vs. the query is a simple perturbation of one of the stored vectors. Compared to exhaustive search, our approach finds the most similar database vectors significantly faster without a noticeable reduction in search quality. Interestingly, the reduction of complexity is provably better in high-dimensional spaces. We empirically demonstrate its practical interest in a large-scale image search scenario with off-the-shelf state-of-the-art descriptors.

cs.CV↗

arXiv2016

Automatic discovery of discriminative parts as a quadratic assignment problem

Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The training of parts is cast as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes. State-of-the art results are obtained on these datasets.

cs.CV↗

arXiv2014

Orientation covariant aggregation of local descriptors with embeddings

Image search systems based on local descriptors typically achieve orientation invariance by aligning the patches on their dominant orientations. Albeit successful, this choice introduces too much invariance because it does not guarantee that the patches are rotated consistently. This paper introduces an aggregation strategy of local descriptors that achieves this covariance property by jointly encoding the angle in the aggregation stage in a continuous manner. It is combined with an efficient monomial embedding to provide a codebook-free method to aggregate local descriptors into a single vector representation. Our strategy is also compatible and employed with several popular encoding methods, in particular bag-of-words, VLAD and the Fisher vector. 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.

cs.CV↗

arXiv2012

The Effective Key Length of Watermarking Schemes

Whereas the embedding distortion, the payload and the robustness of digital watermarking schemes are well understood, the notion of security is still not completely well defined. The approach proposed in the last five years is too theoretical and solely considers the embedding process, which is half of the watermarking scheme. This paper proposes a new measurement of watermarking security, called the effective key length, which captures the difficulty for the adversary to get access to the watermarking channel. This new methodology is applied to additive spread spectrum schemes where theoretical and practical computations of the effective key length are proposed. It shows that these schemes are not secure as soon as the adversary gets observations in the Known Message Attack context.

cs.CR↗

arXiv2011

Anti-sparse coding for approximate nearest neighbor search

This paper proposes a binarization scheme for vectors of high dimension based on the recent concept of anti-sparse coding, and shows its excellent performance for approximate nearest neighbor search. Unlike other binarization schemes, this framework allows, up to a scaling factor, the explicit reconstruction from the binary representation of the original vector. The paper also shows that random projections which are used in Locality Sensitive Hashing algorithms, are significantly outperformed by regular frames for both synthetic and real data if the number of bits exceeds the vector dimensionality, i.e., when high precision is required.

cs.CV↗

arXiv2011

Towards joint decoding of binary Tardos fingerprinting codes

The class of joint decoder of probabilistic fingerprinting codes is of utmost importance in theoretical papers to establish the concept of fingerprint capacity. However, no implementation supporting a large user base is known to date. This article presents an iterative decoder which is, as far as we are aware of, the first practical attempt towards joint decoding. The discriminative feature of the scores benefits on one hand from the side-information of previously accused users, and on the other hand, from recently introduced universal linear decoders for compound channels. Neither the code construction nor the decoder make precise assumptions about the collusion (size or strategy). The extension to incorporate soft outputs from the watermarking layer is straightforward. An extensive experimental work benchmarks the very good performance and offers a clear comparison with previous state-of-the-art decoders.

cs.IT↗

arXiv2010

An Asymmetric Fingerprinting Scheme based on Tardos Codes

Tardos codes are currently the state-of-the-art in the design of practical collusion-resistant fingerprinting codes. Tardos codes rely on a secret vector drawn from a publicly known probability distribution in order to generate each Buyer's fingerprint. For security purposes, this secret vector must not be revealed to the Buyers. To prevent an untrustworthy Provider forging a copy of a Work with an innocent Buyer's fingerprint, previous asymmetric fingerprinting algorithms enforce the idea of the Buyers generating their own fingerprint. Applying this concept to Tardos codes is challenging since the fingerprint must be based on this vector secret. This paper provides the first solution for an asymmetric fingerprinting protocol dedicated to Tardos codes. The motivations come from a new attack, in which an untrustworthy Provider by modifying his secret vector frames an innocent Buyer.

cs.CR↗

arXiv2009

Worst case attacks against binary probabilistic traitor tracing codes

An insightful view into the design of traitor tracing codes should necessarily consider the worst case attacks that the colluders can lead. This paper takes an information-theoretic point of view where the worst case attack is defined as the collusion strategy minimizing the achievable rate of the traitor tracing code. Two different decoders are envisaged, the joint decoder and the simple decoder, as recently defined by P. Moulin \cite{Moulin08universal}. Several classes of colluders are defined with increasing power. The worst case attack is derived for each class and each decoder when applied to Tardos' codes and a probabilistic version of the Boneh-Shaw construction. This contextual study gives the real rates achievable by the binary probabilistic traitor tracing codes. Attacks usually considered in literature, such as majority or minority votes, are indeed largely suboptimal. This article also shows the utmost importance of the time-sharing concept in a probabilistic codes.

cs.IT↗

arXiv2008

The Good, the Bad, and the Ugly: three different approaches to break their watermarking system

The Good is Blondie, a wandering gunman with a strong personal sense of honor. The Bad is Angel Eyes, a sadistic hitman who always hits his mark. The Ugly is Tuco, a Mexican bandit who's always only looking out for himself. Against the backdrop of the BOWS contest, they search for a watermark in gold buried in three images. Each knows only a portion of the gold's exact location, so for the moment they're dependent on each other. However, none are particularly inclined to share...

cs.GR↗

arXiv2007

A constructive and unifying framework for zero-bit watermarking

In the watermark detection scenario, also known as zero-bit watermarking, a watermark, carrying no hidden message, is inserted in content. The watermark detector checks for the presence of this particular weak signal in content. The article looks at this problem from a classical detection theory point of view, but with side information enabled at the embedding side. This means that the watermark signal is a function of the host content. Our study is twofold. The first step is to design the best embedding function for a given detection function, and the best detection function for a given embedding function. This yields two conditions, which are mixed into one `fundamental' partial differential equation. It appears that many famous watermarking schemes are indeed solution to this `fundamental' equation. This study thus gives birth to a constructive framework unifying solutions, so far perceived as very different.

cs.MM↗