Distinctive Image Features from Scale-Invariant Keypoints

By David G. Lowe. 2004

50,284 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model (2015, background): “This success of R-CNN comes from the fact that hand-engineered features like HOG [3] or SIFT [22] are replaced with the high level object representations produced from the last layer of a CNN model.”
Object Detection Networks on Convolutional Feature Maps (2015, methodology): “The Selective Search paper [4] relies on spatial pyramid features [20] on dense SIFT vectors [21] and an additive kernel SVM.”
Going deeper with convolutions (2014, methodology): “The results show that our SST tracker achieves favorable performance than other related sparse trackers [2, 6, 7, 9, 10].”
ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “Section 5.1 documents the progress, starting from coded SIFT features and evolving to large-scale convolutional neural networks dominating at all three tasks of image clas-siﬁcation, single-object localization, and object detection.”
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (2014, background): “The convolutional layers operate in a sliding-window manner and output feature maps which represent the spatial arrangement of the activations (Figure 2).”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “SIFT and HOG are blockwise orientation histograms, a representation we could associate roughly with complex cells in V1, the first cortical area in the primate visual pathway.”
Aggregating Local Image Descriptors into Compact Codes (2012, methodology): “We have used an independent image set for all the learning stages.”
Product Quantization for Nearest Neighbor Search (2011, background): “An exhaustive comparison of the query vector with all codes is prohibitive for very large datasets.”
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (2016, methodology): “For real data such as SIFT vectors [1] (which have complex mixed structure), the performance improvement by increasing the mL is higher, but less prominent at the current settings compared to improvement from the heuristic (see Fig.”
Group Normalization (2018, methodology): “Classical features of SIFT [39], HOG [9], and GIST [41] are group-wise representations by design, where each group of channels is constructed by some kind of histogram.”
Fine-Grained Image Classification via Combining Vision and Language (2017, background): “Early works [14, 15] choose SIFT [45] as features, and the performance is limited.”
Remote Sensing Image Scene Classification: Benchmark and State of the Art (2017, methodology): “Here, we briefly review several most representative handcrafted features, including color histograms [99], texture descriptors [104-106], GIST [107], scale invariant feature transform (SIFT) [108], and histogram of oriented gradients (HOG) [109].”
Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, methodology): “…image representations used in this paper are very basic, in that they rely only on three different kinds of low-level pixel-based perceptual features that capture color, texture (Varma & Zisserman, 2005) and shape information in the form of SIFT descriptors (Lowe, 2004; Vedaldi & Fulkerson, 2008).”
Feature Pyramid Networks for Object Detection (2016, methodology): “Featurized image pyramids were heavily used in the era of hand-engineered features [5, 25].”
Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “Subsequently, it has been applied to multiple tasks like feature point detection [18, 11, 19], face detection [27] and object detection [3, 7, 9].”
An Integrated Micro- and Macroarchitectural Analysis of the Drosophila Brain by Computer-Assisted Serial Section Electron Microscopy (2010, background): “features [31] from nine heavily overlapping images and then”
Aggregated Residual Transformations for Deep Neural Networks (2016, background): “tion Research on visual recognition is undergoing a transition from “feature engineering” to “network engineering” [24,23,43,33,35,37,13]. In contrast to traditional handdesigned features (e.g., SIFT [28] and HOG [5]), features learned by neural networks from large-scale data [32] require minimal hu”
Simultaneous Detection and Segmentation (2014, methodology): “The approaches above were typically built on features such as SIFT[24] or HOG[8].”
A critical analysis of self-supervision, or what we can learn from a single image (2019, methodology): “…to train the ﬁrst few layers of a deep neural networks using a single training image , such as this Image A , B or even C (above), provided that sufﬁcient data augmentation is used. learned and hand-crafted features for visual recognition (Olshausen & Field, 1997; Lowe, 2004; Dalal & Triggs, 2005).”