Learning to Rank Histograms for Object Retrieval

Qin, Danfeng; Chen, Yuhua; Guillaumin, Matthieu; Gool, Luc J. Van

doi:10.5244/c.28.43

Cited by 7 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3 (a) shows that the quantization algorithm is able to discriminate the 4. A similar idea is concurrently proposed in [117], [118] to learn a better similarity for a bag-of-words representation and quantized kernels.…”

Section: Query Performance With Hash Code Rankingmentioning

confidence: 99%

A Survey on Learning to Hash

Wang

Zhang

Song

et al. 2018

IEEE Trans. Pattern Anal. Mach. Intell.

871

411

View full text Add to dashboard Cite

Nearest neighbor search is a problem of finding the data points from the database such that the distances from them to the query point are the smallest. Learning to hash is one of the major solutions to this problem and has been widely studied recently. In this paper, we present a comprehensive survey of the learning to hash algorithms, categorize them according to the manners of preserving the similarities into: pairwise similarity preserving, multiwise similarity preserving, implicit similarity preserving, as well as quantization, and discuss their relations. We separate quantization from pairwise similarity preserving as the objective function is very different though quantization, as we show, can be derived from preserving the pairwise similarities. In addition, we present the evaluation protocols, and the general performance analysis, and point out that the quantization algorithms perform superiorly in terms of search accuracy, search time cost, and space cost. Finally, we introduce a few emerging topics.

show abstract

Section: Query Performance With Hash Code Rankingmentioning

confidence: 99%

A Survey on Learning to Hash

Wang

Zhang

Song

et al. 2018

IEEE Trans. Pattern Anal. Mach. Intell.

871

411

View full text Add to dashboard Cite

show abstract

“…In this work, we learn an embedding where pixels of the same instance are aimed to be close to each other, and we formulate video object segmentation as a pixel-wise retrieval problem. The formulation is inspired also by works in image retrieval [35,31]. Figure 2.…”

Section: Deep Metric Learningmentioning

confidence: 99%

Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning

Chen¹,

Pont-Tuset²,

Montes³

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

281

228

View full text Add to dashboard Cite

This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same object instance into the vicinity of each other, using a fully convolutional network trained by a modified triplet loss as the embedding model. Then the annotated pixels are set as reference and the rest of the pixels are classified using a nearest-neighbor approach. The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario). In the semi-supervised scenario, we achieve results competitive with the state of the art but at a fraction of computation cost (275 milliseconds per frame). In the interactive scenario where the user is able to refine their input iteratively, the proposed method provides instant response to each input, and reaches comparable quality to competing methods with much less interaction.

show abstract

“…All relevant learning-based approaches fall into one or both of the following two categories: (i) learning for an auxiliary task (e.g. some form of distinctiveness of local features [4,15,30,35,58,59,90]), and (ii) learning on top of shallow hand-engineered descriptors that cannot be finetuned for the target task [2,9,24,35,57]. Both of these are in spirit opposite to the core idea behind deep learning that has provided a major boost in performance in various recognition tasks: end-to-end learning.…”

Section: Related Workmentioning

confidence: 99%

NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

Arandjelović

Gronát

Torii

et al. 2018

IEEE Trans. Pattern Anal. Mach. Intell.

446

170

View full text Add to dashboard Cite

We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current stateof-the-art compact image representations on standard image retrieval benchmarks.

show abstract

Learning to Rank Histograms for Object Retrieval

Cited by 7 publications

References 5 publications

A Survey on Learning to Hash

A Survey on Learning to Hash

Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning

NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

Contact Info

Product

Resources

About