Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval

@article{Zhe2018DirectionalSD,
  title={Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval},
  author={Xuefei Zhe and Shifeng Chen and Hong Yan},
  journal={ArXiv},
  year={2018},
  volume={abs/1802.09662}
}

RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection

This work proposes a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process.

A Triplet Nonlocal Neural Network With Dual-Anchor Triplet Loss for High-Resolution Remote Sensing Image Retrieval

This article constructs a triplet nonlocal neural network (T-NLNN) model that combines deep metric learning and nonlocal operation, and proposes a dual-anchor triplet loss function to facilitate the utilization of information in the input samples.

Online Progressive Deep Metric Learning

This work reconsiders the traditional shallow online metric learning and newly develop an online progressive deep metric learning (ODML) framework to construct a metric-algorithm-based deep network that can indeed learn a metric progressively and performs better on the benchmark datasets.

t-vMF Similarity For Regularizing Intra-Class Feature Distribution

  • Takumi Kobayashi
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
This work proposes a method to effectively impose regularization on feature representation learning by focusing on the angle between a feature and a classifier which is embedded in cosine similarity at the classification layer, and forms a novel similarity beyond the cosine based on von Mises-Fisher distribution of directional statistics.

Baggage Image Retrieval with Attention-Based Network for Security Checks

AttentionNet integrates the semantic and recognition tasks using shared convolutional neural networks by multi-task learning and adopts a variant of the triplet loss to perform deep metric learning with an online hard triplet mining strategy.

Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering

The proposed Probabilistic Ranking-based Instance Selection with Memory approach for DML calculates the probability of a label being clean, and filters out potentially noisy samples using a von Mises-Fisher Distribution Similarity distribution for each data class.

Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation

Equipped with the GDMM and the directional appearance model learning module, DDEAL learns static cues from the labeled first frame and dynamically updates cues of the subsequent frames for object segmentation without using online fine-tuning.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Publication Information

Equipped with the global directional matching module and the directional appearance model learning module, DDEAL learns static cues from the labeled first frame and dynamically updates cues of the subsequent frames for object segmentation without using online fine-tuning.

Manifold Preserving CNN for Pixel-Based Object Labelling in Images for High Dimensional Feature spaces

A two-stage end-to-end framework that uses manifold embedding based patch-wise CNN architecture to extract the features and classify the image for labelled classes and has outperformed the previous techniques in accuracy and computation time with a significant margin.
...

References

SHOWING 1-10 OF 55 REFERENCES

Multi-View 3D Object Retrieval With Deep Embedding Network

A deep embedding network jointly supervised by classification loss and triplet loss is proposed to map the high-dimensional image space into a low-dimensional feature space, where the Euclidean distance of features directly corresponds to the semantic similarity of images.

Metric Learning with Adaptive Density Discrimination

This work proposes a novel approach explicitly designed to address a number of subtle yet important issues which have stymied earlier DML algorithms, which maintains an explicit model of the distributions of the different classes in representation space and employs this knowledge to adaptively assess similarity, and achieve local discrimination by penalizing class distribution overlap.

Fast Training of Triplet-Based Deep Binary Embedding Networks

This paper proposes to formulate high-order binary codes learning as a multi-label classification problem by explicitly separating learning into two interleaved stages and proposes to map the original image to compact binary codes via carefully designed deep convolutional neural networks and the hashing function fitting can be solved by training binary CNN classifiers.

FaceNet: A unified embedding for face recognition and clustering

A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.

Improved Deep Metric Learning with Multi-class N-pair Loss Objective

This paper proposes a new metric learning objective called multi-class N-pair loss, which generalizes triplet loss by allowing joint comparison among more than one negative examples and reduces the computational burden of evaluating deep embedding vectors via an efficient batch construction strategy using only N pairs of examples.

SphereFace: Deep Hypersphere Embedding for Face Recognition

This paper proposes the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features in deep face recognition (FR) problem under open-set protocol.

Deep semantic ranking based hashing for multi-label image retrieval

In this work, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features.

Compact Representation for Image Classification: To Choose or to Compress?

This paper argues that feature selection is a better choice than feature compression, and shows that strong multicollinearity among feature dimensions may not exist, which undermines feature compression's effectiveness and renders feature selection a natural choice.

Triplet-Center Loss for Multi-view 3D Object Retrieval

This paper study variants of deep metric learning losses for 3D object retrieval, which did not receive enough attention from this area, and proposes a novel loss named triplet-center loss, which can further enhance the discriminative power of the features.
...