paper-with-me

Papers

GUDN: A novel guide network with label reinforcement strategy for extreme multi-label text classification

2022-01-10 · Qing Wang, Jia Zhu, Hongji Shu, Kwame Omono Asamoah, Jianyang Shi, Cong Zhou

In natural language processing, extreme multi-label text classification is an emerging but essential task. The problem of extreme multi-label text classification (XMTC) is to recall some of the most relevant labels for a text from an extremely large label set. Large-scale pre-trained models have brought a new trend to this problem. Though the large-scale pre-trained models have made significant achievements on this problem, the valuable fine-tuned methods have yet to be studied. Though label semantics have been introduced in XMTC, the vast semantic gap between texts and labels has yet to gain enough attention. This paper builds a new guide network (GUDN) to help fine-tune the pre-trained model to instruct classification later. Furthermore, GUDN uses raw label semantics combined with a helpful label reinforcement strategy to effectively explore the latent space between texts and labels, narrowing the semantic gap, which can further improve predicted accuracy. Experimental results demonstrate that GUDN outperforms state-of-the-art methods on Eurlex-4k and has competitive results on other popular datasets. In an additional experiment, we investigated the input lengths' influence on the Transformer-based model's accuracy. Our source code is released at https://t.hk.uy/aFSH.

📄 PDF Abstract BibTeX arXiv:2201.11582

Code (1)

wq2581/gudn 공식 구현 pytorch

Tasks

4kMulti Label Text ClassificationMulti-Label Text Classificationtext-classificationText Classification

Similar Papers 제목 키워드 기반

RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels

2026-01-19 · Chengzhou Li, Ping Guo, Guanchen Meng, Qi Jia 외 arxiv

Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-…

Object Detection

DEPT: Deep Extreme Point Tracing for Ultrasound Image Segmentation

2025-03-19 · Lei Shi, Xi Fang, Naiyu Wang, Junxing Zhang

Automatic medical image segmentation plays a crucial role in computer aided diagnosis. However, fully supervised learning approaches often require extensive and labor-intensive annotation efforts. To address this challen…

Image SegmentationMedical Image SegmentationSemantic SegmentationWeakly-supervised Learning

You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding

2023-03-26 · Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu

3D scene understanding, e.g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propo…

3D Instance SegmentationInstance SegmentationPseudo LabelRelation Network+3

RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings

2026-04-22 · Wei Han, David Martinez, Anna Khanina, Lawrence Cavedon 외 arxiv

A common strategy in transfer learning is few shot fine-tuning, but its success is highly dependent on the quality of samples selected as training examples. Active learning methods such as uncertainty sampling and divers…

Reinforcement LearningTransfer LearningActive Learning

Cluster-Guided Label Generation in Extreme Multi-Label Classification

2023-02-17 · Taehee Jung, Joo-Kyung Kim, Sungjin Lee, Dongyeop Kang

For extreme multi-label classification (XMC), existing classification-based models poorly perform for tail labels and often ignore the semantic relations among labels, like treating "Wikipedia" and "Wiki" as independent …

ClassificationExtreme Multi-Label ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION