BORRBangladesh Open Research Repository
SearchSubmitAboutContact
BORRResearch for a Better Bangladesh.
AboutSubmit PaperContactTermsPolicyGitHub

© 2026 Bangladesh Open Research Repository.

Filters

Sort By

Sort by dateSort by citations
Year Range
to
Clear all filters

All Papers

16+ results
Field: Domain Adaptation and Few-Shot Learning

Transfer learning: a friendly introduction

Verified

Asmaul Hosna, Ethel Merry, Jigmey Gyalmo, Zulfikar Alom et al.

Journal: Journal Of Big Data
Year: 2022
Citations: 523

Infinite numbers of real-world applications use Machine Learning (ML) techniques to develop potentially the best data available for the users. Transfer learning (TL), one of the categories under ML, has received much attention from the research communities in the past few years. Traditional ML algor...

Physical SciencesComputer ScienceArtificial IntelligenceOpen Access
Read Source

Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition

Verified

Heliang Zheng, Jianlong Fu, Zheng-Jun Zha, Jiebo Luo

Year: 2019Citations: 488

Learning subtle yet discriminative features (e.g., beak and eyes for a bird) plays a significant role in fine-grained image recognition. Existing attention-based approaches localize and amplify significant parts to learn fine-grained details, which often suffer from a limited number of parts and hea...

Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

Exploring Object Relation in Mean Teacher for Cross-Domain Detection

Verified

Qi Cai, Yingwei Pan, Chong‐Wah Ngo, Xinmei Tian et al.

Year: 2019Citations: 356

Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However, simply applying the models learnt on synthetic images may lead to high generalization error on real images due to doma...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Adversarial Spectral Kernel Matching for Unsupervised Time Series Domain Adaptation

Verified

Qiao Liu, Hui Xue

Year: 2021Citations: 82

Unsupervised domain adaptation (UDA) has been received increasing attention since it does not require labels in target domain. Most existing UDA methods learn domain-invariant features by minimizing discrepancy distance computed by a certain metric between domains. However, these discrepancy-based m...

Physical SciencesComputer ScienceArtificial IntelligenceOpen Access
Read Source

From image to language: A critical analysis of Visual Question Answering (VQA) approaches, challenges, and opportunities

Verified

Md Farhan Ishmam, Md Sakib Hossain Shovon, M. F. Mridha, Nilanjan Dey

Journal: Information FusionYear: 2024Citations: 81

The multimodal task of Visual Question Answering (VQA) encompassing elements of Computer Vision (CV) and Natural Language Processing (NLP), aims to generate answers to questions on any visual input. Over time, the scope of VQA has expanded from datasets focusing on an extensive collection of natural...

Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

ALOFT: A Lightweight MLP-Like Architecture with Dynamic Low-Frequency Transform for Domain Generalization

Verified

Jintao Guo, Na Wang, Lei Qi, Yinghuan Shi

Year: 2023Citations: 73

Domain generalization (DG) aims to learn a model that generalizes well to unseen target domains utilizing multiple source domains without re-training. Most existing DG works are based on convolutional neural networks (CNNs). However, the local operation of the convolution kernel makes the model focu...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Show, Deconfound and Tell: Image Captioning with Causal Inference

Verified

Bing Liu, Dong Wang, Xu Yang, Yong Zhou et al.

Journal: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Year: 2022Citations: 66

The transformer-based encoder-decoder framework has shown remarkable performance in image captioning. However, most transformer-based captioning methods ever overlook two kinds of elusive confounders: the visual confounder and the linguistic confounder, which generally lead to harmful bias, induce t...

Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

A Novel Method for Multivariant Pneumonia Classification Based on Hybrid CNN-PCA Based Feature Extraction Using Extreme Learning Machine With CXR Images

Verified

Md. Nahiduzzaman, Md. Omaer Faruq Goni, Md. Shamim Anower, Md. Robiul Islam et al.

Journal: IEEE AccessYear: 2021Citations: 66

In this era of COVID19, proper diagnosis and treatment for pneumonia are very important. Chest X-Ray (CXR) image analysis plays a vital role in the reliable diagnosis of pneumonia. An experienced radiologist is required for this. However, even for an experienced radiographer, it is quite difficult a...

Health SciencesMedicineRadiology, Nuclear Medicine and ImagingOpen Access
Read Source

Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces

Verified

Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe, Pengfei Fang et al.

Journal: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)Year: 2021Citations: 64

Few-shot class incremental learning (FSCIL) aims to incrementally add sets of novel classes to a well-trained base model in multiple training sessions with the restriction that only a few novel instances are available per class. While learning novel classes, FSCIL methods gradually forget base (old)...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Zero-Shot Learning on 3D Point Cloud Objects and Beyond

Verified

Ali Cheraghian, Shafin Rahman, Townim Faisal Chowdhury, Dylan Campbell et al.

Journal: International Journal of Computer VisionYear: 2022Citations: 61

Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However, despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaning...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Zero-Shot Object Detection: Joint Recognition and Localization of Novel Concepts

Verified

Shafin Rahman, Salman H. Khan, Fatih Porikli

Journal: International Journal of Computer VisionYear: 2020Citations: 58
Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation

Verified

Zhonghao Wang, Yunchao Wei, Rogério Feris, Jinjun Xiong et al.

Year: 2020Citations: 56

Utilizing synthetic data for semantic segmentation can significantly relieve human efforts in labelling pixel-level masks. A key challenge of this task is how to alleviate the data distribution discrepancy between the source and target domains, i.e. reducing domain shift. The common approach to this...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

Verified

Jintao Guo, Lei Qi, Yinghuan Shi

Year: 2023Citations: 53

Deep Neural Networks have exhibited considerable success in various visual tasks. However, when applied to unseen test datasets, state-of-the-art models often suffer performance degradation due to domain shifts. In this paper, we introduce a novel approach for domain generalization from a novel pers...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration

Verified

Ziqi Zhou, Lei Qi, Yinghuan Shi

Journal: Lecture notes in computer scienceYear: 2022Citations: 52
Physical SciencesComputer ScienceArtificial Intelligence
Read Source

MetaMixUp: Learning Adaptive Interpolation Policy of MixUp With Metalearning

Verified

Zhijun Mai, Guosheng Hu, Dexiong Chen, Fumin Shen et al.

Journal: IEEE Transactions on Neural Networks and Learning SystemsYear: 2021Citations: 45

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semisupervised learning (SSL), and domain adaption. However, despite its empirical success...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source
PreviousPage 1 of 2+Next