Scalable Feature Matching by Dual Cascaded Scalar Quantization for Image Retrieval

Zhou, Wengang; Yang, Ming; Wang, Xiaoyu; Li, Houqiang; Lin, Yuanqing; Tian, Qi

doi:10.1109/tpami.2015.2430329

Cited by 49 publications

(15 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…methods on the following five benchmark datasets: Holidays [4], UKBench [16], Paris6K [23], Oxford5K [5] and DupImages [24]. The performance on all datasets can be measured by the mean average precision (mAP) [31] expressed as percentages, where the UKBench dataset can also be evaluated using the N-S score (maximum 4) [52].…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…Numerous image retrieval methods based on local descriptors have been proposed [29], [30]. Image retrieval methods typically contain four components including feature extraction, quantization, indexing, and ranking [31]- [35], where most works concentrate on the improvement of feature extraction and the indexing scheme.…”

Section: A Static Match Kernels With Local Descriptorsmentioning

confidence: 99%

“…In particular, Niestér and Stewénius [16] use a visual vocabulary tree to hierarchically quantize SIFT features [6] into visual words. A local descriptor is assigned to its nearest k visual word, and the corresponding term frequency with image label is stored in the entry [31]. The hierarchical construction of the visual vocabulary tree facilitates storing a large amount of visual words and efficient search.…”

Section: A Static Match Kernels With Local Descriptorsmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic Match Kernel With Deep Convolutional Features for Image Retrieval

Yang

Liang

Shen

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

For image retrieval methods based on bag of visual words, much attention has been paid to enhancing the discriminative powers of the local features. Although retrieved images are usually similar to a query in minutiae, they may be significantly different from a semantic perspective, which can be effectively distinguished by convolutional neural networks (CNN). Such images should not be considered as relevant pairs. To tackle this problem, we propose to construct a dynamic match kernel by adaptively calculating the matching thresholds between query and candidate images based on the pairwise distance among deep CNN features. In contrast to the typical static match kernel which is independent to the global appearance of retrieved images, the dynamic one leverages the semantical similarity as a constraint for determining the matches. Accordingly, we propose a semantic-constrained retrieval framework by incorporating the dynamic match kernel, which focuses on matched patches between relevant images and filters out the ones for irrelevant pairs. Furthermore, we demonstrate that the proposed kernel complements recent methods, such as hamming embedding, multiple assignment, local descriptors aggregation, and graph-based re-ranking, while it outperforms the static one under various settings on off-the-shelf evaluation metrics. We also propose to evaluate the matched patches both quantitatively and qualitatively. Extensive experiments on five benchmark data sets and large-scale distractors validate the merits of the proposed method against the state-of-the-art methods for image retrieval.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: A Static Match Kernels With Local Descriptorsmentioning

confidence: 99%

Section: A Static Match Kernels With Local Descriptorsmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Match Kernel With Deep Convolutional Features for Image Retrieval

Yang

Liang

Shen

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Moreover, quantization is of practical usage in areas of signal processing and image retrieval with specific constraints and characteristics. Thus, there are scalar quantization algorithms specifically designed to optimize evaluation metrics of the fields [20,21]. Furthermore, for high-dimensional vector quantization, there have been multiple codebook-based algorithms with various optimization strategies [22,23].…”

Section: Related Workmentioning

confidence: 99%

Scalar Quantization as Sparse Least Square Optimization

Wang

Yang

Fei

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Quantization can be used to form new vectors/matrices with shared values close to the original. In recent years, the popularity of scalar quantization for value-sharing application has been soaring as it has been found huge utilities in reducing the complexity of neural networks. Existing clusteringbased quantization techniques, while being well-developed, have multiple drawbacks including the dependency of the random seed, empty or out-of-the-range clusters, and high time complexity for large number of clusters. To overcome these problems, in this paper, the problem of scalar quantization is examined from a new perspective, namely sparse least square optimization. Specifically, inspired by the property of sparse least square regression, several quantization algorithms based on l 1 least square are proposed. In addition, similar schemes with l 1 + l 2 and l 0 regularization are proposed. Furthermore, to compute quantization results with given amount of values/clusters, this paper designed an iterative method and a clustering-based method, and both of them are built on sparse least square. The paper shows that the latter method is mathematically equivalent to an improved version of k-means clustering-based quantization algorithm, although the two algorithms originated from different intuitions. The algorithms proposed were tested with three types of data and their computational performances, including information loss, time consumption, and the distribution of the values of the sparse vectors, were compared and analyzed. The paper offers a new perspective to probe the area of quantization, and the algorithms proposed can outperform existing methods especially under some bit-width reduction scenarios, when the required post-quantization resolution (number of values) is not significantly lower than the original number.

show abstract

“…Keypoint detection, a fundamental technique in computer vision, has gained extensive attention in recent decades. It plays an important role in various applications such as image retrieval [1], [2], image stitching [3], [4], object recognition [5], [6] and so on. It typically requires finding pixels or blobs which are supposed to be invariant against either photometric or geometric variations.…”

Section: Introductionmentioning

confidence: 99%

Blur-Countering Keypoint Detection via Eigenvalue Asymmetry

Zhang

Akashi

2020

IEEE Access

View full text Add to dashboard Cite

Well-known corner or local extrema feature based detectors such as FAST and DoG have achieved noticeable successes. However, detecting keypoints in the presence of blur has remained to be an unresolved issue. As a matter of fact, various kinds of blur (e.g., motion blur, out-of-focus and space-variant) remarkably increase challenges for keypoint detection. As a result, those methods have limited performance. To settle this issue, we propose a blur-countering method for detecting valid keypoints for various types and degrees of blurred images. Specifically, we first present a distance metric for derivative distributions, which preserves the distinctiveness of patch pairs well under blur. We then model the asymmetry by utilizing the difference of squared eigenvalues based on the distance metric. To make it scale-robust, we also extend it to scale space. The proposed detector is efficient as the main computational cost is the square of derivatives at each pixel. Extensive visual and quantitative results show that our method outperforms current approaches under different types and degrees of blur. Without any parallelization, our implementation achieves real-time performance for low-resolution images (e.g., 320 × 240 pixel).

show abstract

Scalable Feature Matching by Dual Cascaded Scalar Quantization for Image Retrieval

Cited by 49 publications

References 55 publications

Dynamic Match Kernel With Deep Convolutional Features for Image Retrieval

Dynamic Match Kernel With Deep Convolutional Features for Image Retrieval

Scalar Quantization as Sparse Least Square Optimization

Blur-Countering Keypoint Detection via Eigenvalue Asymmetry

Contact Info

Product

Resources

About