Dynamic Sampling for Deep Metric Learning
- URL: http://arxiv.org/abs/2004.11624v2
- Date: Fri, 11 Sep 2020 01:29:01 GMT
- Title: Dynamic Sampling for Deep Metric Learning
- Authors: Chang-Hui Liang, Wan-Lei Zhao, Run-Qing Chen
- Abstract summary: Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold.
A dynamic sampling strategy is proposed to organize the training pairs in an easy-to-hard order to feed into the network.
It allows the network to learn general boundaries between categories from the easy training pairs at its early stages and finalize the details of the model mainly relying on the hard training samples in the later.
- Score: 7.010669841466896
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep metric learning maps visually similar images onto nearby locations and
visually dissimilar images apart from each other in an embedding manifold. The
learning process is mainly based on the supplied image negative and positive
training pairs. In this paper, a dynamic sampling strategy is proposed to
organize the training pairs in an easy-to-hard order to feed into the network.
It allows the network to learn general boundaries between categories from the
easy training pairs at its early stages and finalize the details of the model
mainly relying on the hard training samples in the later. Compared to the
existing training sample mining approaches, the hard samples are mined with
little harm to the learned general model. This dynamic sampling strategy is
formularized as two simple terms that are compatible with various loss
functions. Consistent performance boost is observed when it is integrated with
several popular loss functions on fashion search, fine-grained classification,
and person re-identification tasks.
Related papers
- Integrated Image-Text Based on Semi-supervised Learning for Small Sample Instance Segmentation [1.3157419797035321]
The article proposes a novel small sample instance segmentation solution from the perspective of maximizing the utilization of existing information.
First, it helps the model fully utilize unlabeled data by learning to generate pseudo labels, increasing the number of available samples.
Second, by integrating the features of text and image, more accurate classification results can be obtained.
arXiv Detail & Related papers (2024-10-21T14:44:08Z) - Preview-based Category Contrastive Learning for Knowledge Distillation [53.551002781828146]
We propose a novel preview-based category contrastive learning method for knowledge distillation (PCKD)
It first distills the structural knowledge of both instance-level feature correspondence and the relation between instance features and category centers.
It can explicitly optimize the category representation and explore the distinct correlation between representations of instances and categories.
arXiv Detail & Related papers (2024-10-18T03:31:00Z) - Detection of Under-represented Samples Using Dynamic Batch Training for Brain Tumor Segmentation from MR Images [0.8437187555622164]
Brain tumors in magnetic resonance imaging (MR) are difficult, time-consuming, and prone to human error.
These challenges can be resolved by developing automatic brain tumor segmentation methods from MR images.
Various deep-learning models based on the U-Net have been proposed for the task.
These deep-learning models are trained on a dataset of tumor images and then used for segmenting the masks.
arXiv Detail & Related papers (2024-08-21T21:51:47Z) - EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training [79.96741042766524]
We reformulate the training curriculum as a soft-selection function.
We show that exposing the contents of natural images can be readily achieved by the intensity of data augmentation.
The resulting method, EfficientTrain++, is simple, general, yet surprisingly effective.
arXiv Detail & Related papers (2024-05-14T17:00:43Z) - Partner-Assisted Learning for Few-Shot Image Classification [54.66864961784989]
Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation.
In this paper, we focus on the design of training strategy to obtain an elemental representation such that the prototype of each novel class can be estimated from a few labeled samples.
We propose a two-stage training scheme, which first trains a partner encoder to model pair-wise similarities and extract features serving as soft-anchors, and then trains a main encoder by aligning its outputs with soft-anchors while attempting to maximize classification performance.
arXiv Detail & Related papers (2021-09-15T22:46:19Z) - A Representation Learning Perspective on the Importance of
Train-Validation Splitting in Meta-Learning [14.720411598827365]
splitting data from each task into train and validation sets during meta-training.
We argue that the train-validation split encourages the learned representation to be low-rank without compromising on expressivity.
Since sample efficiency benefits from low-rankness, the splitting strategy will require very few samples to solve unseen test tasks.
arXiv Detail & Related papers (2021-06-29T17:59:33Z) - Few-shot Classification via Adaptive Attention [93.06105498633492]
We propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples.
As demonstrated experimentally, the proposed model achieves state-of-the-art classification results on various benchmark few-shot classification and fine-grained recognition datasets.
arXiv Detail & Related papers (2020-08-06T05:52:59Z) - Expert Training: Task Hardness Aware Meta-Learning for Few-Shot
Classification [62.10696018098057]
We propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly.
A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task.
Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.
arXiv Detail & Related papers (2020-07-13T08:49:00Z) - One-Shot Object Detection without Fine-Tuning [62.39210447209698]
We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module.
We also propose novel training strategies that effectively improve detection performance.
Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
arXiv Detail & Related papers (2020-05-08T01:59:23Z) - PADS: Policy-Adapted Sampling for Visual Similarity Learning [19.950682531209154]
Learning visual similarity requires learning relations, typically between triplets of images.
Currently, the prominent paradigm are fixed or curriculum sampling strategies that are predefined before training starts.
We employ reinforcement learning and have a teacher network adjust the sampling distribution based on the current state of the learner network.
arXiv Detail & Related papers (2020-03-24T21:01:07Z)
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.