English
Related papers

Related papers: Text Classification in the Wild: a Large-scale Lon…

200 papers

This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective…

Computation and Language · Computer Science 2024-09-17 Haode Zhang , Yuwei Zhang , Li-Ming Zhan , Jiaxin Chen , Guangyuan Shi , Albert Y. S. Lam , Xiao-Ming Wu

In the real open world, data tends to follow long-tailed class distributions, motivating the well-studied long-tailed recognition (LTR) problem. Naive training produces models that are biased toward common classes in terms of higher…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Shaden Alshammari , Yu-Xiong Wang , Deva Ramanan , Shu Kong

The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Youngkyu Hong , Seungju Han , Kwanghee Choi , Seokjun Seo , Beomsu Kim , Buru Chang

This paper evaluates Few-Shot Prompting with Large Language Models for Named Entity Recognition (NER). Traditional NER systems rely on extensive labeled datasets, which are costly and time-consuming to obtain. Few-Shot Prompting or…

Information Retrieval · Computer Science 2024-09-05 Hédi Zeghidi , Ludovic Moncla

Label noise is one of the key factors that lead to the poor generalization of deep learning models. Existing label-noise learning methods usually assume that the ground-truth classes of the training data are balanced. However, the…

Machine Learning · Computer Science 2023-08-15 Yang Lu , Yiliang Zhang , Bo Han , Yiu-ming Cheung , Hanzi Wang

Learning from a few examples is an important practical aspect of training classifiers. Various works have examined this aspect quite well. However, all existing approaches assume that the few examples provided are always correctly labeled.…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Pratik Mazumder , Pravendra Singh , Vinay P. Namboodiri

Real-world datasets often exhibit long-tailed distributions, where a few dominant "Head" classes have abundant samples while most "Tail" classes are severely underrepresented, leading to biased learning and poor generalization for the Tail.…

Machine Learning · Computer Science 2026-02-02 Mahdiyar Molahasani , Michael Greenspan , Ali Etemad

This work addresses the task of self-supervised learning (SSL) on a long-tailed dataset that aims to learn balanced and well-separated representations for downstream tasks such as image classification. This task is crucial because the real…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Cuong Manh Hoang , Yeejin Lee , Byeongkeun Kang

With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing…

Computer Vision and Pattern Recognition · Computer Science 2019-01-18 Yin Cui , Menglin Jia , Tsung-Yi Lin , Yang Song , Serge Belongie

Detecting out-of-distribution (OOD) data is essential for safe deployment of deep neural networks (DNNs). This problem becomes particularly challenging in the presence of long-tailed in-distribution (ID) datasets, often leading to high…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Nimeshika Udayangani , Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. As a result, these models fail to generalize to real-world out-of-distribution data. In this work,…

Computation and Language · Computer Science 2021-04-15 Mengnan Du , Varun Manjunatha , Rajiv Jain , Ruchi Deshpande , Franck Dernoncourt , Jiuxiang Gu , Tong Sun , Xia Hu

Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a biased model. Recent studies have made a great effort in…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Mengke Li , Yiu-ming Cheung , Juyong Jiang

Imbalanced music genre classification is a crucial task in the Music Information Retrieval (MIR) field for identifying the long-tail, data-poor genre based on the related music audio segments, which is very prevalent in real-world…

Sound · Computer Science 2022-09-12 Xiaokai Liu , Menghua Zhang

Political scientists often grapple with data scarcity in text classification. Recently, fine-tuned BERT models and their variants have gained traction as effective solutions to address this issue. In this study, we investigate the potential…

Computation and Language · Computer Science 2024-11-11 Yu Wang , Wen Qu , Xin Ye

Large-scale pre-trained language models such as BERT are popular solutions for text classification. Due to the superior performance of these advanced methods, nowadays, people often directly train them for a few epochs and deploy the…

Computation and Language · Computer Science 2023-06-13 Yu-Chen Lin , Si-An Chen , Jie-Jyun Liu , Chih-Jen Lin

Automatic detection and classification of animal sounds has many applications in biodiversity monitoring and animal behaviour. In the past twenty years, the volume of digitised wildlife sound available has massively increased, and automatic…

Pretrained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in domain accuracy. Recent research…

Computation and Language · Computer Science 2024-08-26 Kun Luo , Minghao Qin , Zheng Liu , Shitao Xiao , Jun Zhao , Kang Liu

In the short text, the extremely short length, feature sparsity, and high ambiguity pose huge challenges to classification tasks. Recently, as an effective method for tuning Pre-trained Language Models for specific downstream tasks,…

Computation and Language · Computer Science 2022-04-01 Yi Zhu , Xinke Zhou , Jipeng Qiang , Yun Li , Yunhao Yuan , Xindong Wu

In the real world, long-tailed data distributions are prevalent, making it challenging for models to effectively learn and classify tail classes. However, we discover that in the field of drug chemistry, certain tail classes exhibit higher…

Machine Learning · Computer Science 2025-04-08 Yujia Su , Xinjie Li , Lionel Z. Wang

Large language models (LLMs) have demonstrated remarkable success in NLP tasks. However, there is a paucity of studies that attempt to evaluate their performances on social media-based health-related natural language processing tasks, which…

Computation and Language · Computer Science 2024-03-29 Yuting Guo , Anthony Ovadje , Mohammed Ali Al-Garadi , Abeed Sarker