[Paper] Visual Instance Retrieval with Deep Convolutional Networks

Razavian, Ali Sharif; Sullivan, Josephine; Carlsson, Stefan; Maki, Atsuto

doi:10.3169/mta.4.251

Cited by 306 publications

(314 citation statements)

References 30 publications

(27 reference statements)

Supporting

Mentioning

313

Contrasting

Order By: Relevance

“…The regional MAC descriptors are subsequently sum-pooled along with a series of normalization and PCA-whitening operations [53]. We also note in this survey that several other works [140], [133], [134] also employ similar ideas with [10] in employing max or average pooling on the intermediate feature maps and that Razavian et al [133] are the first. It has been observed that the last convolutional layer (e.g., pool5 in VGGNet), after pooling usually yields superior accuracy to the FC descriptors and the other convolutional layers [134].…”

Section: Feature Encoding and Poolingmentioning

confidence: 99%

“…Again, standard techniques in SIFT-based methods such as HE are employed [156]. Apart from the above-mentioned strategies, we notice that several works [7], [133], [152] extract several region descriptors per image to do a many-to-many matching, called "spatial search" [7]. This method improves the translation and scale invariance of the retrieval system but may encounter efficiency problems.…”

Section: Feature Encoding and Indexingmentioning

confidence: 99%

“…In these works, the 4,096-dim FC features are extracted from the multi-scale image regions [7], [22], [152] or object proposals [147]. On the other hand, Razavian et al [133] also uses the intermediate descriptors after max-pooling as region descriptors.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Each dimension of this descriptor denotes the level of activation of the corresponding detector and resembles the SIFT descriptor to some extent. The column feature initially appears in [133], where Razavian et al first do maxpooling over regularly partitioned windows on the feature maps and then concatenate them across all filter responses, yielding column-like features. In [136], column features from multiple layers of the networks are concatenated, forming the "hypercolumn" feature.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Efficiency for the medium-sized codebook is low because the inverted list contains more postings compared to a large codebook, and the filtering effect of HE methods can only correct this problem to some extent. The retrieval complexity for hybrid methods, as mentioned in Section 4.3, may suffer from the expensive many-to-many matching strategy [7], [133], [152].…”

Section: Efficiency Comparisonsmentioning

confidence: 99%

See 4 more Smart Citations

SIFT Meets CNN: A Decade Survey of Instance Retrieval

Zheng

Yang

Tian

2018

IEEE Trans. Pattern Anal. Mach. Intell.

616

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: Feature Encoding and Poolingmentioning

confidence: 99%

Section: Feature Encoding and Indexingmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: Efficiency Comparisonsmentioning

confidence: 99%

See 3 more Smart Citations

SIFT Meets CNN: A Decade Survey of Instance Retrieval

Zheng

Yang

Tian

2018

IEEE Trans. Pattern Anal. Mach. Intell.

616

319

View full text Add to dashboard Cite

show abstract

In‐Memory Search for Highly Efficient Image Retrieval

Ling

Zhou

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Finding similar images in real time plays a key role in information retrieval and serves as an indispensable function of the search engine. However, image retrieval involves massive distance computation. With the increase in image data volume and dimension, distance computation is suffering from huge power consumption and high computational complexity. Despite the remarkable advantages in energy efficiency shown by nonvolatile content addressable memory (nvCAM)‐based in‐memory search, achieving software‐comparable search accuracy remains a critical challenge under the impact of device variations and other nonideal factors. Here, a heterogeneous image retrieval system combining highly parallel in‐memory search with a high‐precision digital system is reported. Hamming distance (HD) can be calculated in situ with a few memory read operations on the memristor‐based CAM, and several similar images are fetched for further high‐precision rerank in the digital system. This heterogeneous computing system shows high energy efficiency (50×) compared to the CPU and higher search accuracy than the fully in‐memory computing method, thus alleviating the efficiency bottleneck of CPU‐based image retrieval.

show abstract

Deep Shape Matching

Radenović

Tolias

Chum

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

We cast shape matching as metric learning with convolutional networks. We break the end-to-end process of image representation into two parts. Firstly, well established efficient methods are chosen to turn the images into edge maps. Secondly, the network is trained with edge maps of landmark images, which are automatically obtained by a structure-from-motion pipeline. The learned representation is evaluated on a range of different tasks, providing improvements on challenging cases of domain generalization, generic sketch-based image retrieval or its fine-grained counterpart. In contrast to other methods that learn a different model per task, object category, or domain, we use the same network throughout all our experiments, achieving state-of-the-art results in multiple benchmarks.

show abstract

[Paper] Visual Instance Retrieval with Deep Convolutional Networks

Cited by 306 publications

References 30 publications

SIFT Meets CNN: A Decade Survey of Instance Retrieval

SIFT Meets CNN: A Decade Survey of Instance Retrieval

In‐Memory Search for Highly Efficient Image Retrieval

Deep Shape Matching

Contact Info

Product

Resources

About