Domain Specific Data Distillation and Multi-modal Embedding Generation

2024-10-27 · Sharadind Peddiraju, Srini Rajagopal

The challenge of creating domain-centric embeddings arises from the abundance of unstructured data and the scarcity of domain-specific structured data. Conventional embedding techniques often rely on either modality, limiting their applicability and efficacy. This paper introduces a novel modeling approach that leverages structured data to filter noise from unstructured data, resulting in embeddings with high precision and recall for domain-specific attribute prediction. The proposed model operates within a Hybrid Collaborative Filtering (HCF) framework, where generic entity representations are fine-tuned through relevant item prediction tasks. Our experiments, focusing on the cloud computing domain, demonstrate that HCF-based embeddings outperform AutoEncoder-based embeddings (using purely unstructured data), achieving a 28% lift in precision and an 11% lift in recall for domain-specific attribute prediction.

📄 PDF Abstract BibTeX arXiv:2410.20325

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeCloud ComputingCollaborative Filtering Prediction

XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning

2022-11-25 · Pritam Sarkar, Ali Etemad

We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled videos. XKD is trained with two pseudo objectives. First, masked data reconstruction is performed to learn modality-sp…

Action Classification Classification Knowledge Distillation Representation Learning+4

Where Detectors Fail: Closing the Tail-Domain Gap with Expert-Guided Mutual Distillation

2026-07-29 · Xuan Feng, Guihong Liu, Tianlong Gu, Shuai Zhao 외 arxiv

Multimodal fake news detectors often generalize poorly across domains because they learn to trust unreliable evidence: domain-specific shortcuts amplified by imbalanced data and semantically inconsistent text-image pairs…

Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation

2024-09-04 · Yilong Chen, Zongyi Xu, Xiaoshui Huang, Shanshan Zhao 외

Compared to single-modal knowledge distillation, cross-modal knowledge distillation faces more severe challenges due to domain gaps between modalities. Although various methods have proposed various solutions to overcome…

Knowledge Distillation

Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation

2024-10-25 · Yao Wu, Mingwei Xing, Yachao Zhang, Yuan Xie 외

In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target annotation. Previous methods seek to mut…

3D Semantic Segmentation Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation

Domain Adaptation-Based Crossmodal Knowledge Distillation for 3D Semantic Segmentation

2025-08-30 · Jialiang Kang, Jiawen Wang, Dingsheng Luo arxiv

Semantic segmentation of 3D LiDAR data plays a pivotal role in autonomous driving. Traditional approaches rely on extensive annotated data for point cloud analysis, incurring high costs and time investments. In contrast,…

Unsupervised Domain Adaptation 3D Semantic Segmentation Knowledge Distillation Autonomous Driving