Offline Versus Online Triplet Mining Based on Extreme Distances of Histopathology Patches

Sikaroudi, Milad; Ghojogh, Benyamin; Safarpoor, Amir; Karray, Fakhri; Crowley, Mark; Tizhoosh, Hamid R.

doi:10.1007/978-3-030-64556-4_26

Cited by 15 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the contrastive learning mechanism has demonstrated promising performance in self-supervised action recognition. The supervision signals of the contrastive learning paradigm are usually generated by a contrastive loss [19], such as InfoNCE [22], SimCLR [40], MoCo [21], and OTM [23]. These contrastive losses have been widely used in recent selfsupervised action recognition methods.…”

Section: Related Work a Self-supervised Skeleton-based Action Recogni...mentioning

confidence: 99%

“…AimCLR [15] adopts InfoNCE [22] as a contrastive loss to improve the model performance on downstream tasks. In this paper, we use OTM [23] to implement our DMMG.…”

Section: Related Work a Self-supervised Skeleton-based Action Recogni...mentioning

confidence: 99%

“…Those self-supervised action recognition methods [15], [16], [20], [17] first augment skeleton data to construct contrastive pairs (i.e., positive and negative pairs). Then, they learn action features by increasing the similarity between positive pairs while decreasing the similarity between negative pairs using a contrastive loss [21], [22], [23].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition

Guan¹,

Yu²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this work, we propose a new Dual Min-Max Games (DMMG) based self-supervised skeleton action recognition method by augmenting unlabeled data in a contrastive learning framework. Our DMMG consists of a viewpoint variation min-max game and an edge perturbation min-max game. These two min-max games adopt an adversarial paradigm to perform data augmentation on the skeleton sequences and graphstructured body joints, respectively. Our viewpoint variation min-max game focuses on constructing various hard contrastive pairs by generating skeleton sequences from various viewpoints. These hard contrastive pairs help our model learn representative action features, thus facilitating model transfer to downstream tasks. Moreover, our edge perturbation min-max game specializes in building diverse hard contrastive samples through perturbing connectivity strength among graph-based body joints. The connectivity-strength varying contrastive pairs enable the model to capture minimal sufficient information of different actions, such as representative gestures for an action while preventing the model from overfitting. By fully exploiting the proposed DMMG, we can generate sufficient challenging contrastive pairs and thus achieve discriminative action feature representations from unlabeled skeleton data in a self-supervised manner. Extensive experiments demonstrate that our method achieves superior results under various evaluation protocols on widely-used NTU-RGB+D and NTU120-RGB+D datasets.

show abstract

Section: Related Work a Self-supervised Skeleton-based Action Recogni...mentioning

confidence: 99%

“…AimCLR [15] adopts InfoNCE [22] as a contrastive loss to improve the model performance on downstream tasks. In this paper, we use OTM [23] to implement our DMMG.…”

Section: Related Work a Self-supervised Skeleton-based Action Recogni...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition

Guan¹,

Yu²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…While the current batch is processed by the training framework on GPU we generate the next one on CPU. This part can be improved with various triplet generation techniques like hard mining [22,23], but this is not a topic of the current paper therefore we use the simplest random selection.…”

Section: Training 221 Batch Generationmentioning

confidence: 99%

Tiny CNN for feature point description for document analysis: approach and dataset

Sheshkus¹,

Chirvonaya²,

Arlazarov³

2022

Computer Optics

View full text Add to dashboard Cite

In this paper, we study the problem of feature points description in the context of document analysis and template matching. Our study shows that specific training data is required for the task especially if we are to train a lightweight neural network that will be usable on devices with limited computational resources. In this paper, we construct and provide a dataset of photo and synthetically generated images and a method of training patches generation from it. We prove the effectiveness of this data by training a lightweight neural network and show how it performs in both general and documents patches matching. The training was done on the provided dataset in comparison with HPatches training dataset and for the testing, we solve HPatches testing framework tasks and template matching task on two publicly available datasets with various documents pictured on complex backgrounds: MIDV-500 and MIDV-2019.

show abstract

“…showed [ 9 ] that triplet mining is useful, and can be performed efficiently. Online triplet mining—the method where triplets are selected right before the training step—is performing remarkably better than its counterpart ( offline mining), where embeddings are unaffected by the last steps [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Metric Learning Using Negative Sampling Probability Annealing

Kertész

2022

Sensors

View full text Add to dashboard Cite

Multiple studies have concluded that the selection of input samples is key for deep metric learning. For triplet networks, the selection of the anchor, positive, and negative pairs is referred to as triplet mining. The selection of the negatives is considered the be the most complicated task, due to a large number of possibilities. The goal is to select a negative that results in a positive triplet loss; however, there are multiple approaches for this—semi-hard negative mining or hardest mining are well-known in addition to random selection. Since its introduction, semi-hard mining was proven to outperform other negative mining techniques; however, in recent years, the selection of the so-called hardest negative has shown promising results in different experiments. This paper introduces a novel negative sampling solution based on dynamic policy switching, referred to as negative sampling probability annealing, which aims to exploit the positives of all approaches. Results are validated on an experimental synthetic dataset using cluster-analysis methods; finally, the discriminative abilities of trained models are measured on real-life data.

show abstract

Offline Versus Online Triplet Mining Based on Extreme Distances of Histopathology Patches

Cited by 15 publications

References 19 publications

DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition

DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition

Tiny CNN for feature point description for document analysis: approach and dataset

Deep Metric Learning Using Negative Sampling Probability Annealing

Contact Info

Product

Resources

About