Learning Spread-Out Local Feature Descriptors

By Xu Zhang, Felix X. Yu, Sanjiv Kumar, Shih-Fu Chang. 2017

150 citations recorded by the source corpus.

We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors. The idea is that in order to fully utilize the expressive power of the descriptor space, good local feature descriptors should be sufficiently “spread-out” over the space. In this work, we propose a regularization term to maximize the spread in feature descriptor inspired by the property of uniform distribution. We show that the proposed regularization with triplet loss outperforms existing Euclidean distance based descriptor learning techniques by a large margin. As an extension, the proposed regularization technique can also be used to improve image-level deep feature embedding.

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

Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, methodology): “With such assumption, we try to separate each instance from all the other sampled instances within the batch, resulting in a spread-out property [52].”
How To Backdoor Federated Learning (2018, background): “Another defense [10] targets sybil attacks by exploiting the observation that in high-dimensional spaces, random vectors are orthogonal [48].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “…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 to the output of deep…”
R2D2: Repeatable and Reliable Detector and Descriptor (2019, methodology): “Ranking losses have thus been extensively and successfully used to train local descriptors ( e.g . triplet loss [6, 3, 21, 55, 29, 61]).”
Self-supervised Learning for Large-scale Item Recommendations (2020, methodology): “Spread-out Regularization.”
Hard negative examples are hard, but useful (2020, background): “In [29], the authors proposed a spread out regularization to let local feature descriptors fully utilize the expressive power of the space.”
Federated Learning with Only Positive Labels (2020, methodology): “A similar objective was first proposed as a regularizer to improve learning discriminative visual descriptors (Zhang et al., 2017) and then used in extreme-multiclass classification (Guo et al.”
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].”
Heated-Up Softmax Embedding (2018, background): “In other words, two randomly sampled samples from different categories are close to orthogonal (Zhang et al., 2017).”