Learning local feature descriptors with triplets and shallow convolutional neural networks

By Vassileios Balntas, Edgar Riba, Daniel Ponsa, Krystian Mikolajczyk. 2016

595 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Learning Spread-Out Local Feature Descriptors (2017, methodology): “In the experiment section, we test combining the global orthogonal regularization with contractive loss3 (1) [19], triplet loss (2) [1], lifted structured similarity softmax loss (LSSS) [14] and N-pair loss [21].”
Task-Free Continual Learning (2018, methodology): “Since the input consists of two tracks of two different identities, we use the triplet margin loss [4] which has been shown to work well in face recognition applications.”
Deep Anomaly Detection with Outlier Exposure (2018, background): “The FPRN metric (Liu et al., 2018; Kumar et al., 2016; Balntas et al., 2016) is the probability that an in-distribution example (negative) raises a false alarm when N% of anomalous examples (positive) are detected, so a lower FPRN is better.”
Distilling portable Generative Adversarial Networks for Image Translation (2020, unknown): “Triplet loss, proposed by (Balntas et al. 2016), optimizes the black space such that samples with the same identity are closer to each other than those with different identity.”
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis (2019, methodology): “To train the networks for this task, we use the triplet loss approach [30], [31].”
Neighbourhood Consensus Networks (2018, unknown): “…of trainable image descriptors are based on convolutional neural networks (CNNs) and typically operate on patches extracted using a feature detector such as DoG [23], yielding a sparse set of descriptors [17, 10, 3, 37, 36, 4] or use a pre-trained image-level CNN feature extractor [26, 32].”
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency (2022, methodology): “Inspired by the triplet loss [59], we design (STF i − S i + δ) as a term of consistency loss LC,i where δ is a given constant margin to keep negative samples far apart [60].”
R2D2: Repeatable and Reliable Detector and Descriptor (2019, methodology): “Most deep feature matching meth-ods have focused on learning the descriptor component, applied either on a sparse set of keypoints [3, 51, 52, 29] detected using standard handcrafted methods or densely over the image [12, 47, 54, 32].”
Working hard to know your neighbor's margins: Local descriptor learning loss (2017, methodology): “Oxford5k Paris6k Descriptor BoW BoW+SV BoW+QE BoW BoW+SV BoW+QE TFeat-M* [23] 46.”
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features (2019, methodology): “2a illustrates the common variations of this pipeline, from using hand-crafted detectors [7,19,29,31,33] and descriptors [7,9,24,29,44], replacing either the descriptor [6,54,55] or detector [49,68] with a learned alternative, or learning both the detector and descriptor [38,64].”
Continual Learning in Neural Networks (2019, methodology): “Since the input consists of two tracks of two different identities, we use the triplet margin loss [14] which has been shown to work well in face recognition applications.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “…and Komodakis 2015; Han et al. 2015; Kedem et al. 2012; Wang et al. 2017; Weinberger and Saul 2009) and descriptor learning (Simo-Serra et al. 2015; Balntas et al. 2016a, 2017; Zhang et al. 2017c; Mishchuk et al. 2017; Wei et al. 2018; He et al. 2018; Tian et al. 2019; Luo et al. 2019), according…”
HPatches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors (2017, methodology): “Finally, we evaluate several recent deep descriptors including the siamese variants of DeepCompare [41] (DCS, DC-S2S) with one and two stream CNN architectures for one or two patch crops, DeepDesc [30] (DDESC), which exploits hard-negative mining, and the TFeat margin* (TFM) and ratio* (TF-R) of the”
Comparative Evaluation of Hand-Crafted and Learned Local Features (2017, methodology): “The authors of LIFT and TFeat make a first step to provide more insight into the practicality of the descriptors in a real-world application.”
Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings (2019, methodology): “Intriplet hard negative mining with anchor swap [37] is used as a loss function for learning an embedding sensitive to the l2 metric”
Semantic Search in Millions of Equations (2020, methodology): “The triplet loss [2] we have previously used [20], contrasts the similarity between a positive pair of examples and a negative pair of examples and demands that the similar pair has a higher similarity by a user-defined margin ∆, usually set to 1.”
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning (2019, methodology): “, DeepDesc(DDesc) [34], TFeat [2], L2Net [36], HardNet(HNet) [26], HardNet with GOR [41], Scale-Aware Descriptor [17], DOAP [15] and GeoDesc [22].”
Image Matching Across Wide Baselines: From Paper to Practice (2020, background): “They include Deepdesc [92], TFeat [13], L2-Net [100], HardNet [61], SOSNet [101], and LogPolarDesc [38] – most of them are trained on the same dataset [24].”