Results 1 - 10
of
26
PERSON RE-IDENTIFICATION BY MANIFOLD RANKING
"... Existing person re-identification methods conventionally rely on labelled pairwise data to learn a task-specific distance metric for ranking. The value of unlabelled gallery instances is generally overlooked. In this study, we show that it is possible to propagate the query information along the unl ..."
Abstract
-
Cited by 18 (2 self)
- Add to MetaCart
(Show Context)
Existing person re-identification methods conventionally rely on labelled pairwise data to learn a task-specific distance metric for ranking. The value of unlabelled gallery instances is generally overlooked. In this study, we show that it is possible to propagate the query information along the unlabelled data manifold in an unsupervised way to obtain robust ranking results. In addition, we demonstrate that the performance of existing supervised metric learning methods can be significantly boosted once integrated into the proposed manifold ranking-based framework. Extensive evaluation is conducted on three benchmark datasets. Index Terms — person re-identification, manifold, ranking, distance metric learning, video surveillance 1.
POP: Person Re-Identification Post-Rank Optimisation
"... Owing to visual ambiguities and disparities, person re-identification methods inevitably produce suboptimal rank-list, which still requires exhaustive human eyeballing to identify the correct target from hundreds of different likely-candidates. Existing re-identification studies focus on im-proving ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(Show Context)
Owing to visual ambiguities and disparities, person re-identification methods inevitably produce suboptimal rank-list, which still requires exhaustive human eyeballing to identify the correct target from hundreds of different likely-candidates. Existing re-identification studies focus on im-proving the ranking performance, but rarely look into the critical problem of optimising the time-consuming and error-prone post-rank visual search at the user end. In this study, we present a novel one-shot Post-rank OPtimisation (POP) method, which allows a user to quickly refine their search by either “one-shot ” or a couple of sparse negative selections during a re-identification process. We conduct systematic behavioural studies to understand user’s search-ing behaviour and show that the proposed method allows correct re-identification to converge 2.6 times faster than the conventional exhaustive search. Importantly, through extensive evaluations we demonstrate that the method is ca-pable of achieving significant improvement over the state-of-the-art distance metric learning based ranking models, even with just “one shot ” feedback optimisation, by as much as over 30 % performance improvement for rank 1 re-identification on the VIPeR and i-LIDS datasets. 1.
Semi-Supervised Learning with Manifold Fitted Graphs
"... In this paper, we propose a locality-constrained and sparsity-encouraged manifold fitting approach, aiming at capturing the locally sparse manifold structure into neighborhood graph construction by exploiting a principled optimization model. The proposed model formulates neighborhood graph construct ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
In this paper, we propose a locality-constrained and sparsity-encouraged manifold fitting approach, aiming at capturing the locally sparse manifold structure into neighborhood graph construction by exploiting a principled optimization model. The proposed model formulates neighborhood graph construction as a sparse coding problem with the locality constraint, therefore achieving simultaneous neighbor selection and edge weight optimization. The core idea underlying our model is to perform a sparse manifold fitting task for each data point so that close-by points lying on the same local manifold are automatically chosen to connect and meanwhile the connection weights are acquired by simple geometric reconstruction. We term the novel neighborhood graph generated by our proposed optimization model M-Fitted Graph since such a graph stems from sparse manifold fitting. To evaluate the robustness and effectiveness of M-fitted graphs, we leverage graph-based semi-supervised learning as the testbed. Extensive experiments carried out on six benchmark datasets validate that the proposed M-fitted graph is superior to stateof-the-art neighborhood graphs in terms of classification accuracy using popular graph-based semisupervised learning methods. 1
Harmonious Hashing
- PROCEEDINGS OF THE TWENTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
"... Hashing-based fast nearest neighbor search technique has attracted great attention in both research and industry areas recently. Many existing hashing approaches encode data with projection-based hash functions and represent each projected dimension by 1-bit. However, the dimensions with high varian ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
Hashing-based fast nearest neighbor search technique has attracted great attention in both research and industry areas recently. Many existing hashing approaches encode data with projection-based hash functions and represent each projected dimension by 1-bit. However, the dimensions with high variance hold large energy or information of data but treated equivalently as dimensions with low variance, which leads to a serious information loss. In this paper, we introduce a novel hashing algorithm called Harmonious Hashing which aims at learning hash functions with low information loss. Specifically, we learn a set of optimized projections to preserve the maximum cumulative energy and meet the constraint of equivalent variance on each dimension as much as possible. In this way, we could minimize the information loss after binarization. Despite the extreme simplicity, our method outperforms superiorly to many state-of-the-art hashing methods in large-scale and high-dimensional nearest neighbor search experiments.
Multi-Manifold Ranking: Using Multiple Features for Better Image Retrieval
"... Abstract. Manifold Ranking (MR) is one of the most popular graphbased ranking methods and has been widely used for information retrieval. Due to its ability to capture the geometric structure of the image set, it has been successfully used for image retrieval. The existing approaches that use manifo ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Manifold Ranking (MR) is one of the most popular graphbased ranking methods and has been widely used for information retrieval. Due to its ability to capture the geometric structure of the image set, it has been successfully used for image retrieval. The existing approaches that use manifold ranking rely only on a single image manifold. However, such methods may not fully discover the geometric structure of the image set and may lead to poor precision results. Motivated by this, we propose a novel method named Multi-Manifold Ranking (MMR) which embeds multiple image manifolds each constructed using a different image feature. We propose a novel cost function that is minimized to obtain the ranking scores of the images. Our proposed multi-manifold ranking has a better ability to explore the geometric structure of image set as demonstrated by our experiments. Furthermore, to improve the efficiency of MMR, a specific graph called anchor graph is incorporated into MMR. The extensive experiments on real world image databases demonstrate that MMR outperforms existing manifold ranking based methods in terms of quality and has comparable running time to the fastest MR algorithm. Key words: Image retrieval, integrated features, manifold ranking 1
Large-Scale Machine Learning for Classification and Search
, 2012
"... With the rapid development of the Internet, nowadays tremendous amounts of data including images and videos, up to millions or billions, can be collected for training machine learning models. Inspired by this trend, this thesis is dedicated to developing large-scale machine learning techniques for t ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
With the rapid development of the Internet, nowadays tremendous amounts of data including images and videos, up to millions or billions, can be collected for training machine learning models. Inspired by this trend, this thesis is dedicated to developing large-scale machine learning techniques for the purpose of making classification and nearest neighbor search practical on gigantic databases. Our first approach is to explore data graphs to aid classification and nearest neighbor search. A graph offers an attractive way of representing data and discovering the essential information such as the neighborhood structure. However, both of the graph construction process and graph-based learning techniques become computationally prohibitive at a large scale. To this end, we present an efficient large graph construction approach and subsequently apply it to develop scalable semi-supervised learning and unsupervised hashing algorithms. Our unique contributions on the graph-related topics include: 1. Large Graph Construction: Conventional neighborhood graphs such as kNN graphs require a quadratic time complexity, which is inadequate for large-scale applications mentioned above. To overcome this bottleneck, we present a novel graph construction approach,
Efficient label propagation
- In ICML
, 2014
"... Label propagation is a popular graph-based semi-supervised learning framework. So as to obtain the optimal labeling scores, the label propagation algorithm requires an inverse matrix which in-curs the high computational cost ofO(n3+cn2), where n and c are the numbers of data points and labels, respe ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Label propagation is a popular graph-based semi-supervised learning framework. So as to obtain the optimal labeling scores, the label propagation algorithm requires an inverse matrix which in-curs the high computational cost ofO(n3+cn2), where n and c are the numbers of data points and labels, respectively. This paper proposes an effi-cient label propagation algorithm that guarantees exactly the same labeling results as those yielded by optimal labeling scores. The key to our ap-proach is to iteratively compute lower and upper bounds of labeling scores to prune unnecessary score computations. This idea significantly re-duces the computational cost to O(cnt) where t is the average number of iterations for each label and t ≪ n in practice. Experiments demonstrate the significant superiority of our algorithm over existing label propagation methods. 1.
Parallel Field Ranking
"... Recently, ranking data with respect to the intrinsic geometric structure (manifold ranking) has received considerable attentions, with encouraging performance in many applications in pattern recognition, information retrieval and recommendation systems. Most of the existing manifold ranking methods ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Recently, ranking data with respect to the intrinsic geometric structure (manifold ranking) has received considerable attentions, with encouraging performance in many applications in pattern recognition, information retrieval and recommendation systems. Most of the existing manifold ranking methods focus on learning a ranking function that varies smoothly along the data manifold. However, beyond smoothness, a desirable ranking function should vary monotonically along the geodesics of the data manifold, such that the ranking order along the geodesics is preserved. In this paper, we aim to learn a ranking function that varies linearly and therefore monotonically along the geodesics of the data manifold. Recent theoretical work shows that the gradient field of a linear function on the manifold has to be a parallel vector field. Therefore, we propose a novel ranking algorithm on the data manifolds, called Parallel Field Ranking. Specifically, we try to learn a ranking function and a vector field simultaneously. We require the vector field to be close to the gradient field of the ranking function, and the vector field to be as parallel as possible. Moreover, we require the value of the ranking function at the query point to be the highest, and then decrease linearly along the manifold. Experimental results on both synthetic data and real data demonstrate the effectiveness of our proposed algorithm.
Face recognition via archetype hull ranking
- In Proc. ICCV
, 2013
"... The archetype hull model is playing an important role in large-scale data analytics and mining, but rarely applied to vision problems. In this paper, we migrate such a geometric model to address face recognition and verification together through proposing a unified archetype hull ranking frame-work. ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
The archetype hull model is playing an important role in large-scale data analytics and mining, but rarely applied to vision problems. In this paper, we migrate such a geometric model to address face recognition and verification together through proposing a unified archetype hull ranking frame-work. Upon a scalable graph characterized by a compact set of archetype exemplars whose convex hull encompasses most of the training images, the proposed framework ex-plicitly captures the relevance between any query and the stored archetypes, yielding a rank vector over the archetype hull. The archetype hull ranking is then executed on ev-ery block of face images to generate a blockwise similarity measure that is achieved by comparing two different rank vectors with respect to the same archetype hull. After inte-grating blockwise similarity measurements with learned im-portance weights, we accomplish a sensible face similarity measure which can support robust and effective face recog-nition and verification. We evaluate the face similarity mea-sure in terms of experiments performed on three benchmark face databases Multi-PIE, Pubfig83, and LFW, demonstrat-ing its performance superior to the state-of-the-arts. 1.
Learning Local Semantic Distances with Limited Supervision
"... Abstract—Recent advances in distance function learning have demonstrated that learning a good distance metric can greatly improve the performance in a wide variety of tasks in data mining and web search. A major problem in such scenarios is the limited labeled knowledge available for learning the us ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Recent advances in distance function learning have demonstrated that learning a good distance metric can greatly improve the performance in a wide variety of tasks in data mining and web search. A major problem in such scenarios is the limited labeled knowledge available for learning the user intentions. Furthermore, distances are inherently local, where a single global distance function may not capture the distance structure well. A challenge here is that local distance learning is even harder when the labeled information available is limited, because the distance function varies with data locality. To address these issues, we propose a local metric learning algorithm termed Local Semantic Sensing (LSS), which augments the small amount of labeled data with unlabeled data in order to learn the semantic information in the manifold structure, and then integrated with supervised intentional knowledge in a local way. We present results in a retrieval application, which show that the approach significantly outperforms other state-of-the-art methods in the literature. I.
