Three Things to Know about Deep Metric Learning

• URL: http://arxiv.org/abs/2412.12432v1
• Date: Tue, 17 Dec 2024 00:49:12 GMT
• Title: Three Things to Know about Deep Metric Learning
• Authors: Yash Patel, Giorgos Tolias, Jiri Matas,
• Abstract summary: This paper addresses supervised deep metric learning for open-set image retrieval. It focuses on three key aspects: the loss function, mixup regularization, and model initialization. Through a systematic study of these components, we demonstrate that their synergy enables large models to nearly solve popular benchmarks.
• Score: 34.16300515811057
• License:
• Abstract: This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization. In deep metric learning, optimizing the retrieval evaluation metric, recall@k, via gradient descent is desirable but challenging due to its non-differentiable nature. To overcome this, we propose a differentiable surrogate loss that is computed on large batches, nearly equivalent to the entire training set. This computationally intensive process is made feasible through an implementation that bypasses the GPU memory limitations. Additionally, we introduce an efficient mixup regularization technique that operates on pairwise scalar similarities, effectively increasing the batch size even further. The training process is further enhanced by initializing the vision encoder using foundational models, which are pre-trained on large-scale datasets. Through a systematic study of these components, we demonstrate that their synergy enables large models to nearly solve popular benchmarks.

Related papers

• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• Adaptive Cross Batch Normalization for Metric Learning [75.91093210956116]
  Metric learning is a fundamental problem in computer vision. We show that it is equally important to ensure that the accumulated embeddings are up to date. In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration.
  arXiv  Detail & Related papers  (2023-03-30T03:22:52Z)
• Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training [1.116812194101501]
  The paper presents a simple and effective learning-based method for computing a discriminative 3D point cloud descriptor. We employ recent advances in image retrieval and propose a modified version of a loss function based on a differentiable average precision approximation.
  arXiv  Detail & Related papers  (2022-03-02T09:29:28Z)
• Relational Surrogate Loss Learning [41.61184221367546]
  This paper revisits the surrogate loss learning, where a deep neural network is employed to approximate the evaluation metrics. In this paper, we show that directly maintaining the relation of models between surrogate losses and metrics suffices. Our method is much easier to optimize and enjoys significant efficiency and performance gains.
  arXiv  Detail & Related papers  (2022-02-26T17:32:57Z)
• Adaptive Hierarchical Similarity Metric Learning with Noisy Labels [138.41576366096137]
  We propose an Adaptive Hierarchical Similarity Metric Learning method. It considers two noise-insensitive information, textiti.e., class-wise divergence and sample-wise consistency. Our method achieves state-of-the-art performance compared with current deep metric learning approaches.
  arXiv  Detail & Related papers  (2021-10-29T02:12:18Z)
• Recall@k Surrogate Loss with Large Batches and Similarity Mixup [62.67458021725227]
  Direct optimization, by gradient descent, of an evaluation metric is not possible when it is non-differentiable. In this work, a differentiable surrogate loss for the recall is proposed. The proposed method achieves state-of-the-art results in several image retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-08-25T11:09:11Z)
• More Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning [3.9596068699962315]
  Continual Learning has become that of addressing the stability-plasticity dilemma of connectionist systems. We propose an analysis of the memory quantity/quality trade-off adopting various data reduction approaches to increase the number of instances storable in memory. Our findings suggest that the optimal trade-off is severely skewed toward instance quantity, where rehearsal approaches with several heavily compressed instances easily outperform state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-05-28T21:05:51Z)
• Mixed-Privacy Forgetting in Deep Networks [114.3840147070712]
  We show that the influence of a subset of the training samples can be removed from the weights of a network trained on large-scale image classification tasks. Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting. We show that our method allows forgetting without having to trade off the model accuracy.
  arXiv  Detail & Related papers  (2020-12-24T19:34:56Z)
• Deep Optimized Priors for 3D Shape Modeling and Reconstruction [38.79018852887249]
  We introduce a new learning framework for 3D modeling and reconstruction. We show that the proposed strategy effectively breaks the barriers constrained by the pre-trained priors.
  arXiv  Detail & Related papers  (2020-12-14T03:56:31Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning [17.19890778916312]
  We propose an augmentation method in an embedding space for pair-based metric learning losses, called embedding expansion. Because of its simplicity and flexibility, it can be used for existing metric learning losses without affecting model size, training speed, or optimization difficulty.
  arXiv  Detail & Related papers  (2020-03-05T11:43:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.