English
Related papers

Related papers: Perceive, Act and Correct: Confidence Is Not Enoug…

200 papers

Pre-trained code models have recently achieved substantial improvements in many code intelligence tasks. These models are first pre-trained on large-scale unlabeled datasets in a task-agnostic manner using self-supervised learning, and then…

Software Engineering · Computer Science 2024-01-11 Shuzheng Gao , Wenxin Mao , Cuiyun Gao , Li Li , Xing Hu , Xin Xia , Michael R. Lyu

Although Physics-Informed Neural Networks (PINNs) have been successfully applied in a wide variety of science and engineering fields, they can fail to accurately predict the underlying solution in slightly challenging…

Machine Learning · Computer Science 2023-03-27 Yufeng Wang , Cong Xu , Min Yang , Jin Zhang

Open Set Recognition (OSR) requires models not only to accurately classify known classes but also to effectively reject unknown samples. However, when unknown samples are semantically similar to known classes, inter-class overlap in the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Dongdong Zhao , Ranxin Fang , Changtian Song , Zhihui Liu , Jianwen Xiang

We propose to bridge the gap between semi-supervised and unsupervised image recognition with a flexible method that performs well for both generalized category discovery (GCD) and image clustering. Despite the overlap in motivation between…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Gihan Jayatilaka , Abhinav Shrivastava , Matthew Gwilliam

Modern end-to-end automatic speech recognition (ASR) models like Whisper not only suffer from reduced recognition accuracy in noise, but also exhibit overconfidence - assigning high confidence to wrong predictions. We conduct a systematic…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-10 Mingyue Huo , Yuheng Zhang , Yan Tang

Confidence-based pseudo-label selection usually generates overly confident yet incorrect predictions, due to the early misleadingness of model and overfitting inaccurate pseudo-labels in the learning process, which heavily degrades the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Peng Zhang , Zhihui Lai , Heng Kong

Consistency regularization-based methods are prevalent in semi-supervised learning (SSL) algorithms due to their exceptional performance. However, they mainly depend on domain-specific data augmentations, which are not usable in domains…

Machine Learning · Computer Science 2023-09-29 Matin Moezzi

In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Haifei Zhang , Patrick Barry , Eduardo Brandao

The incompleteness of positive labels and the presence of many unlabelled instances are common problems in binary classification applications such as in review helpfulness classification. Various studies from the classification literature…

Information Retrieval · Computer Science 2020-08-17 Xi Wang , Iadh Ounis , Craig Macdonald

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Machine Learning · Computer Science 2024-08-12 Pietro Morerio , Ruggero Ragonesi , Vittorio Murino

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

Machine Learning · Computer Science 2023-08-08 Shuang Ao , Stefan Rueger , Advaith Siddharthan

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Chen Gong , Kong Bin , Eric J. Seibel , Xin Wang , Youbing Yin , Qi Song

The assessment of binary classifier performance traditionally centers on discriminative ability using metrics, such as accuracy. However, these metrics often disregard the model's inherent uncertainty, especially when dealing with sensitive…

Machine Learning · Computer Science 2024-02-13 Agathe Fernandes Machado , Arthur Charpentier , Emmanuel Flachaire , Ewen Gallic , François Hu

Positive and Unlabeled (PU) learning, a binary classification model trained with only positive and unlabeled data, generally suffers from overfitted risk estimation due to inconsistent data distributions. To address this, we introduce a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Chengjie Wang , Chengming Xu , Zhenye Gan , Jianlong Hu , Wenbing Zhu , Lizhuag Ma

Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…

Computer Vision and Pattern Recognition · Computer Science 2024-06-26 Yangdi Lu , Wenbo He

Deep neural models have achieved state of the art performance on a wide range of problems in computer science, especially in computer vision. However, deep neural networks often require large datasets of labeled samples to generalize…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Patrick Kage , Jay C. Rothenberger , Pavlos Andreadis , Dimitrios I. Diochnos

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Jiaxiang Liu , Yuan Wang , Jiawei Du , Joey Tianyi Zhou , Mingkun Xu , Zuozhu Liu

Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) against a human…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Jacob Piland , Chris Sweet , Adam Czajka

Network traffic classification (NTC) is vital for efficient network management, security, and performance optimization, particularly with 5G/6G technologies. Traditional methods, such as deep packet inspection (DPI) and port-based…

Networking and Internet Architecture · Computer Science 2025-09-30 Ehsan Eslami , Walaa Hamouda

Semi-supervised learning (SSL) provides an effective means of leveraging unlabelled data to improve a model performance. Even though the domain has received a considerable amount of attention in the past years, most methods present the…

Machine Learning · Statistics 2023-03-06 Hugo Schmutz , Olivier Humbert , Pierre-Alexandre Mattei