Improving Deep Metric Learning by Divide and Conquer

@article{Sanakoyeu2021ImprovingDM,
  title={Improving Deep Metric Learning by Divide and Conquer},
  author={Artsiom Sanakoyeu and Pingchuan Ma and Vadim Tschernezki and Bj{\"o}rn Ommer},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  year={2021},
  volume={PP}
}
Deep metric learning aims at learning a mapping from the input domain to an embedding space, where semantically similar objects are located nearby and dissimilar objects far from another. However, while the embedding space learns to mimic the user-provided similarity on the training data, it should also generalize to novel categories not seen during training. Besides user-provided training labels, a lot of additional visual factors (such as viewpoint changes or shape peculiarities) exist and… 

Introspective Deep Metric Learning

TLDR
An introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images that attains state-of-the-art performance on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets for image retrieval.

Prototype Memory for Large-Scale Face Representation Learning

TLDR
A novel face representation learning model called Prototype Memory, which alleviates "prototype obsolescence" and allows training on a dataset of any size and can be used with various loss functions, hard example mining algorithms and encoder architectures.

References

SHOWING 1-10 OF 107 REFERENCES

Divide and Conquer the Embedding Space for Metric Learning

TLDR
This work proposes a novel easy-to-implement divide and conquer approach for deep metric learning, which significantly improves the state-of-the-art performance of metric learning and outperforms the state of theart by a large margin in retrieval, clustering and re-identification tasks.

Deep Metric Learning via Lifted Structured Feature Embedding

TLDR
An algorithm for taking full advantage of the training batches in the neural network training by lifting the vector of pairwise distances within the batch to the matrix of Pairwise distances enables the algorithm to learn the state of the art feature embedding by optimizing a novel structured prediction objective on the lifted problem.

Ensemble Deep Manifold Similarity Learning Using Hard Proxies

TLDR
A new time- and memory-efficient method for estimating the manifold similarities by using a closed-form convergence solution of the Random Walk algorithm that outperforms the state of the art in both image retrieval and clustering on the benchmark CUB-200-2011, Cars196, and Stanford Online Products datasets.

MIC: Mining Interclass Characteristics for Improved Metric Learning

TLDR
This work proposes a novel surrogate task to learn visual characteristics shared across classes with a separate encoder, trained jointly with the encoder for class information by reducing their mutual information.

Making Classification Competitive for Deep Metric Learning

TLDR
It is demonstrated that a standard classification network can be transformed into a variant of proxy-based metric learning that is competitive against non-parametric approaches across a wide variety of image retrieval tasks and can learn high-dimensional binary embeddings that achieve new state-of-the-art performance.

Attention-based Ensemble for Deep Metric Learning

TLDR
An attention-based ensemble, which uses multiple attention masks so that each learner can attend to different parts of the object, which outperforms the state-of-the-art methods by a significant margin on image retrieval tasks.

Deep Variational Metric Learning

TLDR
This paper proposes a deep variational metric learning (DVML) framework to explicitly model the intra-class variance and disentangle the intra -class invariance, namely, the class centers, and can simultaneously generate discriminative samples to improve robustness.

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

TLDR
This work divides the last embedding layer of a deep network into an embedding ensemble and forms the task of training this ensemble as an online gradient boosting problem, and proposes two loss functions which increase the diversity in this ensemble.

Improved Embeddings with Easy Positive Triplet Mining

TLDR
This paper proposes an alternative, loosened embedding strategy that requires the embedding function only map each training image to the most similar examples from the same class, an approach it is called "Easy Positive" mining.

Ranked List Loss for Deep Metric Learning

TLDR
This work presents two limitations of existing ranking-motivated structured losses and proposes a novel ranked list loss to solve both of them and proposes to learn a hypersphere for each class in order to preserve the similarity structure inside it.
...