MatchNet: Unifying feature and metric learning for patch-based matching

By Xufeng Han, Thomas K. Leung, Yangqing Jia, Rahul Sukthankar, Alexander C. Berg. 2015

866 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

CrossTransformers: spatially-aware few-shot transfer (2020, background): “Discriminative parts [5, 10, 22, 34, 42, 83] and visual words [74, 100] have a rich history, and have found applications in deformable-parts models [26], and classification [70, 100].”
Learning Deep Structure-Preserving Image-Text Embeddings (2015, background): “Finally, our work is related to deep similarity learning [4, 6, 7, 16, 18, 39, 47], though we are solving a cross-view, not a within-view, matching problem.”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “…only considering works that apply to a single, static image we can indicatively list successes of CNNs in superresolution [24], colorization [55], boundary detection [6,28,49,107], symmetry detection [91], interest point detection [109], image descriptors [35, 92, 110], surface Input Boundaries”
Learning Spread-Out Local Feature Descriptors (2017, methodology): “Though our method is flexible in terms of the patch sizes, here we follow [6] to use patch size 64 × 64.”
Learning to Compare: Relation Network for Few-Shot Learning (2017, background): “In contrast, our framework further defines a relation classifier CNN, in the style of [33, 44, 14] (While [33] focuses on reasoning about relation between two objects in a same image which is to address a different problem.”
A New Representation of Skeleton Sequences for 3D Action Recognition (2017, methodology): “The pre-trained CNN model is leveraged as a feature extractor due to the fact that the CNN features extracted by the models pre-trained with ImageNet [22] are very powerful and have been successfully applied in a number of cross-domain applications [3, 6, 21, 10].”
Learning a Multi-View Stereo Machine (2017, background): “Most recently, CNN based learning methods have been proposed for 3D reconstruction by learning image patch similarity functions [60, 18, 23] and end-to-end disparity regression from stereo pairs [37, 28].”
Matterport3D: Learning from RGB-D Data in Indoor Environments (2017, background): “With the recent success of neural networks, several works have begun to explore the use of deep learning techniques for training state-of-the-art keypoint descriptors that can facilitate robust matching between keypoints and their local image features [45, 34, 16].”
Learning Two-Branch Neural Networks for Image-Text Matching Tasks (2017, background): “Our two-branch networks are related to Siamese networks for metric learning [44], [45], [46], [47], [48], [49].”
Unsupervised Learning of Depth and Ego-Motion from Video (2017, background): “, feature matching [18], pose estimation [26], and stereo [10, 27, 53].”
Dense Human Body Correspondences Using Convolutional Networks (2015, background): “Several recent papers [27, 15, 49, 14] have successfully used this idea for finding correspondences between 2D images, and have shown that descriptors learned from deep neural networks are significantly better than generic pixel-wise descriptors in this context.”
Generic 3D Representation via Pose Estimation and Matching (2016, background): “Therefore, we presume (and empirically observe) that the generality of our 3D representation is mostly attributed to the camera pose estimation component. scribing, and matching image features, either through a handcrafting the feature [35,11,39,38,5,40] or learning it [50,25,65,9,66,49,19].”
Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimizing Global Loss Functions (2015, methodology): “However, these methods have been shown to produce significantly worse classification results on the UBC dataset [1, 3, 30] than the recently proposed siamese deep ConvNets [12, 20, 36] (note that the UBC dataset is a benchmark dataset that has been used to compare local image descriptors).”
Mining on Manifolds: Metric Learning Without Labels (2018, neutral): “These tasks include particular object retrieval [15], local descriptor learning [17], ranking [62], and nearest-neighbor regression [6].”
Geometric deep learning (2016, background): “A popular choice is to let the network extract each pixel descriptor using a neighboring patch (c.f.[ 33, 104]).”
On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location (2020, methodology): “Examples of region cropping in CNNs include: The bounding box in object detection [27, 34, 79]; processing a huge resolution image in patches [42, 86]; local image region matching [32, 66, 108, 107]; local CNN patch pooling encoders [3, 6, 8].”