Boundary-restricted metric learning

Chen, Shuo; Gong, Chen; Li, Xiang; Yang, Jian; Niu, Gang; Sugiyama, Masashi

doi:10.1007/s10994-023-06380-3

Cited by 3 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, contrastive learning treats them on equal grounds by pushing them apart. To address this issue, Large-margin Contrastive Learning was first established by Chen et al [26] to distinguish intra-cluster and inter-cluster pairings, with the goal of driving the inter-cluster pairs away. None of them have addressed the issue of mode collapse, and they have also not selected meaningful feature blocks during contrastive learning.…”

Section: Contrastive Learningmentioning

confidence: 99%

Multi-attention bidirectional contrastive learning method for unpaired image-to-image translation

Yang,

Liu,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Unpaired image-to-image translation (I2IT) involves establishing an effective mapping between the source and target domains to enable cross-domain image transformation. Previous contrastive learning methods inadequately accounted for the variations in features between two domains and the interrelatedness of elements within the features. Consequently, this can result in challenges encompassing model instability and the blurring of image edge features. To this end, we propose a multi-attention bidirectional contrastive learning method for unpaired I2IT, referred to as MabCUT. We design separate embedding blocks for each domain based on depthwise separable convolutions and train them simultaneously from both the source and target domains. Then we utilize a pixel-level multi-attention extractor to query images from embedding blocks in order to select feature blocks with crucial information, thus preserving essential features from the source domain. To enhance the feature representation capability of the model, we incorporate depthwise separable convolutions for the generator. We conducted comprehensive evaluations using three datasets, demonstrating that our approach enhances the quality of unpaired I2IT while avoiding the issue of mode collapse-related image blurring.

show abstract

Section: Contrastive Learningmentioning

confidence: 99%

Multi-attention bidirectional contrastive learning method for unpaired image-to-image translation

Yang,

Liu,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…To tackle the limitations above, we propose a novel Probability-Polarized OT (PPOT) framework for UDA. Inspired by pioneering work (Chen et al 2021), which applies polarization regularization to distance metric, we introduce the polarization mechanism to the OT plan and propose the Probability Polarization (PP) regularizer for OT. Mathematically, PPOT imposes a margin constraint on the probability couplings by introducing thresholds for the positive transport and negative transport, i.e., transportations between intra-class pairs and inter-class pairs.…”

Section: Introductionmentioning

confidence: 99%

Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation

Wang,

Ren,

Zhai

et al. 2024

AAAI

View full text Add to dashboard Cite

Optimal transport (OT) is an important methodology to measure distribution discrepancy, which has achieved promising performance in artificial intelligence applications, e.g., unsupervised domain adaptation. However, from the view of transportation, there are still limitations: 1) the local discriminative structures for downstream tasks, e.g., cluster structure for classification, cannot be explicitly admitted by the learned OT plan; 2) the entropy regularization induces a dense OT plan with increasing uncertainty. To tackle these issues, we propose a novel Probability-Polarized OT (PPOT) framework, which can characterize the structure of OT plan explicitly. Specifically, the probability polarization mechanism is proposed to guide the optimization direction of OT plan, which generates a clear margin between similar and dissimilar transport pairs and reduces the uncertainty. Further, a dynamic mechanism for margin is developed by incorporating task-related information into the polarization, which directly captures the intra/inter class correspondence for knowledge transportation. A mathematical understanding for PPOT is provided from the view of gradient, which ensures interpretability. Extensive experiments on several datasets validate the effectiveness and empirical efficiency of PPOT.

show abstract

Research on Clothing Image Retrieval Combining Topology Features with Color Texture Features

Zhang,

Sun,

2024

Mathematics

View full text Add to dashboard Cite

Topological data analysis (TDA) is a method of feature extraction based on data topological structure. Image feature extraction using TDA has been shown to be superior to other feature extraction techniques in some problems, so it has recently received the attention of researchers. In this paper, clothing image retrieval based on topology features and color texture features is studied. The main work is as follows: (1) Based on the analysis of image data by persistent homology, the feature construction method of a topology feature histogram is proposed, which can represent the ruler of image local topological data, and make up for the shortcomings of traditional feature extraction methods. (2) The improvement of Wasserstein distance is presented, while the similarity measure method named topology feature histogram distance is proposed. (3) Because the single feature has some problems such as the incomplete description of image information and poor robustness, the clothing image retrieval is realized by combining the topology feature with the color texture feature. The experimental results show that the proposed algorithm, namely topology feature histogram + corresponding distance, can effectively reduce the computation time while ensuring the accuracy. Compared with the method using only color texture, the retrieval rate of top5 is improved by 14.9%. Compared with the method using cubic complex + Wasserstein distance, the retrieval rate of top5 is improved by 3.8%, while saving 3.93 s computation time.

show abstract

Boundary-restricted metric learning

Cited by 3 publications

References 45 publications

Multi-attention bidirectional contrastive learning method for unpaired image-to-image translation

Multi-attention bidirectional contrastive learning method for unpaired image-to-image translation

Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation

Research on Clothing Image Retrieval Combining Topology Features with Color Texture Features

Contact Info

Product

Resources

About