Sparse Quantization for Patch Description
Xavier Boix,Michael Gygli,Gemma Roig,Luc Van Gool +3 more
- pp 2842-2849
Reads0
Chats0
TLDR
This work presents a novel formulation of patch description, that achieves state-of-the-art results for two key point matching benchmarks, namely those by Brown and Mikolajczyk and PASCAL VOC07.Abstract:
The representation of local image patches is crucial for the good performance and efficiency of many vision tasks. Patch descriptors have been designed to generalize towards diverse variations, depending on the application, as well as the desired compromise between accuracy and efficiency. We present a novel formulation of patch description, that serves such issues well. Sparse quantization lies at its heart. This allows for efficient encodings, leading to powerful, novel binary descriptors, yet also to the generalization of existing descriptors like SIFT or BRIEF. We demonstrate the capabilities of our formulation for both key point matching and image classification. Our binary descriptors achieve state-of-the-art results for two key point matching benchmarks, namely those by Brown and Mikolajczyk. For image classification, we propose new descriptors, that perform similar to SIFT on Caltech101 and PASCAL VOC07.read more
Citations
More filters
Proceedings ArticleDOI
Learning to compare image patches via convolutional neural networks
Sergey Zagoruyko,Nikos Komodakis +1 more
TL;DR: This paper shows how to learn directly from image data a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems, and opts for a CNN-based model that is trained to account for a wide variety of changes in image appearance.
Proceedings ArticleDOI
L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space
Yurun Tian,Bin Fan,Fuchao Wu +2 more
TL;DR: The good generalization ability shown by experiments indicates that L2-Net can serve as a direct substitution of the existing handcrafted descriptors as well as a progressive sampling strategy which enables the network to access billions of training samples in a few epochs.
Posted Content
Learning to Compare Image Patches via Convolutional Neural Networks
Sergey Zagoruyko,Nikos Komodakis +1 more
TL;DR: In this paper, a CNN-based model is trained to account for a wide variety of changes in image appearance, which can significantly outperform the state-of-the-art on several problems.
Journal ArticleDOI
Learning Local Feature Descriptors Using Convex Optimisation
TL;DR: It is shown that learning the pooling regions for the descriptor can be formulated as a convex optimisation problem selecting the regions using sparsity, and an extension of the learning formulations to a weakly supervised case, which allows us to learn the descriptors from unannotated image collections.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Book ChapterDOI
SURF: speeded up robust features
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Journal ArticleDOI
Speeded-Up Robust Features (SURF)
TL;DR: A novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Proceedings ArticleDOI
ORB: An efficient alternative to SIFT or SURF
TL;DR: This paper proposes a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise, and demonstrates through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations.