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

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

Deconfounded Image Captioning: A Causal Retrospect

Verified

Xu Yang, Hanwang Zhang, Jianfei Cai

Journal: arXiv (Cornell University)
Year: 2020
Citations: 38

Dataset bias in vision-language tasks is becoming one of the main problems which hinders the progress of our community. Existing solutions lack a principled analysis about why modern image captioners easily collapse into dataset bias. In this paper, we present a novel perspective: Deconfounded Image...

Physical SciencesComputer ScienceComputer Vision and Pattern RecognitionOpen Access
Read Source

Auto-Parsing Network for Image Captioning and Visual Question Answering

Verified

Xu Yang, Chongyang Gao, Hanwang Zhang, Jianfei Cai

Journal: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)Year: 2021Citations: 36

We propose an Auto-Parsing Network (APN) to discover and exploit the input data’s hidden tree structures for improving the effectiveness of the Transformer-based vision-language systems. Specifically, we impose a Probabilistic Graphical Model (PGM) parameterized by the attention operations on each s...

Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning

Verified

Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi et al.

Year: 2020Citations: 36

Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different types, harboring inherently different characteristics, e.g....

Physical SciencesComputer ScienceArtificial IntelligenceOpen Access
Read Source

An Efficient Recognition Method for Handwritten Arabic Numerals Using CNN with Data Augmentation and Dropout

Verified

Akm Ashiquzzaman, Abdul Kawsar Tushar, Md Ashiqur Rahman, Farzana Mohsin

Journal: Advances in intelligent systems and computingYear: 2018Citations: 35
Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

BT-Net: An end-to-end multi-task architecture for brain tumor classification, segmentation, and localization from MRI images

Verified

Salman Fazle Rabby, Muhammad Abdullah Arafat, Taufiq Hasan

Journal: ArrayYear: 2024Citations: 34

Brain tumors are severe medical conditions that can prove fatal if not detected and treated early. Radiologists often use MRI and CT scan imaging to diagnose brain tumors early. However, a shortage of skilled radiologists to analyze medical images can be problematic in low-resource healthcare settin...

Physical SciencesComputer ScienceComputer Vision and Pattern RecognitionOpen Access
Read Source

MFF: Multi-modal feature fusion for zero-shot learning

Verified

Weipeng Cao, Yuhao Wu, Chengchao Huang, Muhammed J. A. Patwary et al.

Journal: NeurocomputingYear: 2022Citations: 34
Physical SciencesComputer ScienceArtificial Intelligence
Read Source

DomainAdaptor: A Novel Approach to Test-time Adaptation

Verified

Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Year: 2023Citations: 33

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test. In this paper, we investigate a more challenging task that a...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction

Verified

Yan Yang, Md Zakir Hossain, Eric A. Stone, Shafin Rahman

Journal: 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)Year: 2023Citations: 29

Spatial transcriptomics (ST) is essential for understanding diseases and developing novel treatments. It measures gene expression of each fine-grained area (i.e., different windows) in the tissue slide with low throughput. This paper proposes an Exemplar Guided Network (EGN) to accurately and effici...

Life SciencesBiochemistry, Genetics and Molecular BiologyMolecular Biology
Read Source

Joint Adversarial Learning for Domain Adaptation in Semantic Segmentation

Verified

Yixin Zhang, Zilei Wang

Journal: Proceedings of the AAAI Conference on Artificial IntelligenceYear: 2020Citations: 29

Unsupervised domain adaptation in semantic segmentation is to exploit the pixel-level annotated samples in the source domain to aid the segmentation of unlabeled samples in the target domain. For such a task, the key point is to learn domain-invariant representations and adversarial learning is usua...

Physical SciencesComputer ScienceArtificial IntelligenceOpen Access
Read Source

A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis

Verified

Sadia Islam Tonni, Md. Alif Sheakh, Mst. Sazia Tahosin, Md. Zahid Hasan et al.

Journal: Advanced Intelligent SystemsYear: 2025Citations: 27

Brain tumors are among the most severe health challenges, necessitating early and precise diagnosis for effective treatment planning. This study introduces an optimized hybrid transfer learning (TL) framework for brain tumor classification using magnetic resonance imaging images. The proposed system...

Life SciencesNeuroscienceNeurologyOpen Access
Read Source

IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

Verified

Zekun Li, Lei Qi, Yinghuan Shi, Yang Gao

Year: 2023Citations: 27

Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain. Unfortunately, in many real-world applications, the collected unlabeled data will inevitably contain unseen-class outliers not belonging to any of the labeled classes. To deal with the challen...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

VDD: Varied Drone Dataset for semantic segmentation

Verified

Wenxiao Cai, 克己 阿久津, Jinyan Hou, Cong Guo et al.

Journal: Journal of Visual Communication and Image RepresentationYear: 2025Citations: 22
Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

Disturbance-immune weight sharing for neural architecture search

Verified

Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yong Guo et al.

Journal: Neural NetworksYear: 2021Citations: 22

Neural architecture search (NAS) has gained increasing attention in the community of architecture design. One of the key factors behind the success lies in the training efficiency brought by the weight sharing (WS) technique. However, WS-based NAS methods often suffer from a performance disturbance ...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

VG-CALF: A vision-guided cross-attention and late-fusion network for radiology images in Medical Visual Question Answering

Verified

Aiman Lameesa, Chaklam Silpasuwanchai, Md. Sakib Bin Alam

Journal: NeurocomputingYear: 2024Citations: 21
Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

Continual Test-time Domain Adaptation via Dynamic Sample Selection

Verified

Yanshuo Wang, Jie Hong, Ali Cheraghian, Shafin Rahman et al.

Year: 2024Citations: 21

The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA. DSS consists of dynamic thresholding, positive learning, an...

Physical SciencesComputer ScienceInformation Systems
Read Source
PreviousPage 2 of 3+Next