Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors

Qin, Danfeng; Gammeter, Stephan; Bossard, Lukas; Quack, Till; Gool, Luc Van

doi:10.1109/cvpr.2011.5995373

Cited by 268 publications

(184 citation statements)

References 10 publications

Supporting

Mentioning

183

Contrasting

Unclassified

Order By: Relevance

“…The learned weight vector is used to compute the average query. Other important extensions include "hello neighbor" based on reciprocal neighbors [116], QE with rank-based weighting [111], Hamming QE [89] (see Section 3.5), etc.…”

Section: Query Expansionmentioning

confidence: 99%

SIFT Meets CNN: A Decade Survey of Instance Retrieval

Zheng

Yang

Tian

2018

IEEE Trans. Pattern Anal. Mach. Intell.

656

319

View full text Add to dashboard Cite

Abstract-In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

show abstract

Section: Query Expansionmentioning

confidence: 99%

SIFT Meets CNN: A Decade Survey of Instance Retrieval

Zheng

Yang

Tian

2018

IEEE Trans. Pattern Anal. Mach. Intell.

656

319

View full text Add to dashboard Cite

show abstract

“…This implies that the learned affinities better estimate the true geodesic distances on the underlying data manifolds. In particular, this means that the learned affinities can improve any distance-based image retrieval method, e.g., [31]. On all test datasets, the proposed method achieves excellent results, which are significantly better than baseline results obtained with original affinities.…”

Section: Performance Evaluation With Image Retrieval Ratesmentioning

confidence: 52%

“…With setting K ¼ 20, the learned similarities improve the results to mAP ¼ 68:5%. It is still not as good as some of the state-of-art retrieval results, [41], [31]. However, as we emphasize, we do not propose a stand-alone image retrieval algorithm.…”

Section: Inria Holidays Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Affinity Learning with Diffusion on Tensor Product Graph

Yang

Prasad

Latecki

2013

IEEE Trans. Pattern Anal. Mach. Intell.

145

127

View full text Add to dashboard Cite

Abstract-In many applications, we are given a finite set of data points sampled from a data manifold and represented as a graph with edge weights determined by pairwise similarities of the samples. Often the pairwise similarities (which are also called affinities) are unreliable due to noise or due to intrinsic difficulties in estimating similarity values of the samples. As observed in several recent approaches, more reliable similarities can be obtained if the original similarities are diffused in the context of other data points, where the context of each point is a set of points most similar to it. Compared to the existing methods, our approach differs in two main aspects. First, instead of diffusing the similarity information on the original graph, we propose to utilize the tensor product graph (TPG) obtained by the tensor product of the original graph with itself. Since TPG takes into account higher order information, it is not a surprise that we obtain more reliable similarities. However, it comes at the price of higher order computational complexity and storage requirement. The key contribution of the proposed approach is that the information propagation on TPG can be computed with the same computational complexity and the same amount of storage as the propagation on the original graph. We prove that a graph diffusion process on TPG is equivalent to a novel iterative algorithm on the original graph, which is guaranteed to converge. After its convergence we obtain new edge weights that can be interpreted as new, learned affinities. We stress that the affinities are learned in an unsupervised setting. We illustrate the benefits of the proposed approach for data manifolds composed of shapes, images, and image patches on two very different tasks of image retrieval and image segmentation. With learned affinities, we achieve the bull's eye retrieval score of 99.99 percent on the MPEG-7 shape dataset, which is much higher than the state-of-the-art algorithms. When the data points are image patches, the NCut with the learned affinities not only significantly outperforms the NCut with the original affinities, but it also outperforms state-of-the-art image segmentation methods.

show abstract

“…Even though it is not presented as a MQIR method it can be extended to perform MQIR. They combine multiple retrieval sets using a graph based link analysis method and k-reciprocal nearest neighbors [19]. In the work of Liu et al [12], a textual query based image retrieval method is presented that uses labeled positive/negative images downloaded from the internet to train a classifier.…”

Section: Related Workmentioning

confidence: 99%