A Robust Contrastive Alignment Method For Multi-Domain Text Classification

2022-04-26 · Xuefeng Li, Hao Lei, LiWen Wang, Guanting Dong, Jinzheng Zhao, Jiachi Liu, Weiran Xu, Chunyun Zhang

Multi-domain text classification can automatically classify texts in various scenarios. Due to the diversity of human languages, texts with the same label in different domains may differ greatly, which brings challenges to the multi-domain text classification. Current advanced methods use the private-shared paradigm, capturing domain-shared features by a shared encoder, and training a private encoder for each domain to extract domain-specific features. However, in realistic scenarios, these methods suffer from inefficiency as new domains are constantly emerging. In this paper, we propose a robust contrastive alignment method to align text classification features of various domains in the same feature space by supervised contrastive learning. By this means, we only need two universal feature extractors to achieve multi-domain text classification. Extensive experimental results show that our method performs on par with or sometimes better than the state-of-the-art method, which uses the complex multi-classifier in a private-shared framework.

📄 PDF Abstract BibTeX arXiv:2204.12125

Code (0)

등록된 구현이 없습니다.

Tasks

Classification Contrastive LearningDiversitytext-classification Text Classification

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment

2026-01-31 · Lukas Kuhn, Giuseppe Serra, Florian Buettner arxiv

Vision-language models have transformed multimodal representation learning, yet dominant contrastive approaches like CLIP require large batch sizes, careful negative sampling, and extensive hyperparameter tuning. We intr…

Representation Learning

Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages

2023-06-13 · Simon Durand, Daniel Stoller, Sebastian Ewert

Lyrics alignment gained considerable attention in recent years. State-of-the-art systems either re-use established speech recognition toolkits, or design end-to-end solutions involving a Connectionist Temporal Classifica…

Contrastive Learning speech-recognition Speech Recognition

Domain Aligned CLIP for Few-shot Classification

2023-11-15 · Muhammad Waleed Gondal, Jochen Gast, Inigo Alonso Ruiz, Richard Droste 외

Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via cont…

Benchmarking Classification Domain Adaptation image-classification+2

Spatio-temporal Contrastive Domain Adaptation for Action Recognition

2021-06-19 · CVPR 2021 1 · Xiaolin Song, Sicheng Zhao, Jingyu Yang, Huanjing Yue 외

Unsupervised domain adaptation (UDA) for human action recognition is a practical and challenging problem. Compared with image-based UDA, video-based UDA is comprehensive to bridge the domain shift on both spatial rep…

Action Recognition Contrastive Learning Domain Adaptation Self-Supervised Learning+2

FLAVARS: A Multimodal Foundational Language and Vision Alignment Model for Remote Sensing

2025-01-14 · Isaac Corley, Simone Fobi Nsutezo, Anthony Ortiz, Caleb Robinson 외

Remote sensing imagery is dense with objects and contextual visual information. There is a recent trend to combine paired satellite images and text captions for pretraining performant encoders for downstream tasks. Howev…

Classification Contrastive Learning Semantic Segmentation zero-shot-classification+1