English
Related papers

Related papers: A Novel Two-Step Fine-Tuning Pipeline for Cold-Sta…

200 papers

In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some…

Computation and Language · Computer Science 2025-09-30 Hakaze Cho , Peng Luo , Mariko Kato , Rin Kaenbyou , Naoya Inoue

Deep learning models for natural language processing rely heavily on high-quality labeled datasets. However, existing labeling approaches often struggle to balance label quality with labeling cost. To address this challenge, we propose…

Human-Computer Interaction · Computer Science 2026-02-17 Guozheng Li , Ao Wang , Shaoxiang Wang , Yu Zhang , Pengcheng Cao , Yang Bai , Chi Harold Liu

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…

Computation and Language · Computer Science 2019-11-15 Itzik Malkiel , Lior Wolf

Screening documents is a tedious and time-consuming aspect of high-recall retrieval tasks, such as compiling a systematic literature review, where the goal is to identify all relevant documents for a topic. To help streamline this process,…

Information Retrieval · Computer Science 2024-07-02 Xinyu Mao , Bevan Koopman , Guido Zuccon

The introduction of the Transformer neural network, along with techniques like self-supervised pre-training and transfer learning, has paved the way for advanced models like BERT. Despite BERT's impressive performance, opportunities for…

Computation and Language · Computer Science 2024-07-02 Farnaz Zeidi , Mehmet Fatih Amasyali , Çiğdem Erol

Speech emotion recognition (SER) has garnered increasing attention due to its wide range of applications in various fields, including human-machine interaction, virtual assistants, and mental health assistance. However, existing SER methods…

Sound · Computer Science 2024-05-02 Dongyuan Li , Ying Zhang , Yusong Wang , Funakoshi Kataro , Manabu Okumura

Test-time adaptation (TTA) adapts the pre-trained models during inference using unlabeled test data and has received a lot of research attention due to its potential practical value. Unfortunately, without any label supervision, existing…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Longhui Yuan , Shuang Li , Zhuo He , Binhui Xie

Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-based end-to-end MOT models achieve strong performance by explicitly modeling temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Riku Inoue , Shogo Sato , Kazuhiko Murasaki , Tomoyasu Shimada , Toshihiko Nishimura , Ryuichi Tanida

Accurate segmentation annotations are critical for disease monitoring, yet manual labeling remains a major bottleneck due to the time and expertise required. Active learning (AL) alleviates this burden by prioritizing informative samples…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Devon Levy , Bar Assayag , Laura Gaspar , Ilan Shimshoni , Bella Specktor-Fadida

Active learning, a label-efficient paradigm, empowers models to interactively query an oracle for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem from the sheer volume of point clouds, rendering…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Binhui Xie , Shuang Li , Qingju Guo , Chi Harold Liu , Xinjing Cheng

Active learning is a commonly used approach that reduces the labeling effort required to train deep neural networks. However, the effectiveness of current active learning methods is limited by their closed-world assumptions, which assume…

Machine Learning · Computer Science 2024-01-11 Ruiyu Mao , Ouyang Xu , Yunhui Guo

Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive. Although useful priors such as foundation models or crowdsourced datasets are available, they are…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Hoyoung Kim , Sehyun Hwang , Suha Kwak , Jungseul Ok

Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test…

Machine Learning · Computer Science 2022-01-25 Tianyang Wang , Xingjian Li , Pengkun Yang , Guosheng Hu , Xiangrui Zeng , Siyu Huang , Cheng-Zhong Xu , Min Xu

Active Label Correction (ALC) has emerged as a promising solution to the high cost and error-prone nature of manual pixel-wise annotation in semantic segmentation, by actively identifying and correcting mislabeled data. Although recent work…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Youjin Jeon , Kyusik Cho , Suhan Woo , Euntai Kim

While pre-trained language model (PLM) fine-tuning has achieved strong performance in many NLP tasks, the fine-tuning stage can be still demanding in labeled data. Recent works have resorted to active fine-tuning to improve the label…

Computation and Language · Computer Science 2022-05-04 Yue Yu , Lingkai Kong , Jieyu Zhang , Rongzhi Zhang , Chao Zhang

Automatic readability assessment (ARA) is the task of evaluating the level of ease or difficulty of text documents for a target audience. For researchers, one of the many open problems in the field is to make such models trained for the…

Computation and Language · Computer Science 2021-08-02 Joseph Marvin Imperial

Text Classification finds interesting applications in the pickup and delivery services industry where customers require one or more items to be picked up from a location and delivered to a certain destination. Classifying these customer…

Information Retrieval · Computer Science 2021-09-21 Sumanth Prabhu , Moosa Mohamed , Hemant Misra

Contextual Embeddings have yielded state-of-the-art results in various natural language processing tasks. However, these embeddings are constrained by models requiring large amounts of data and huge computing power. This is an issue for…

Computation and Language · Computer Science 2024-11-28 Biraj Silwal

Given two large lists of records, the task in entity resolution (ER) is to find the pairs from the Cartesian product of the lists that correspond to the same real world entity. Typically, passive learning methods on such tasks require large…

Databases · Computer Science 2022-01-19 Arjit Jain , Sunita Sarawagi , Prithviraj Sen

Stream-based active learning (AL) is an efficient training data collection method, and it is used to reduce human annotation cost required in machine learning. However, it is difficult to say that the human cost is low enough because most…

Robotics · Computer Science 2023-10-04 Kanata Suzuki , Taro Sunagawa , Tomotake Sasaki , Takashi Katoh