相关论文: AdaFocal: Calibration-aware Adaptive Focal Loss

In this work, we quantitatively calibrate the performance of global and local models in federated learning through a multi-criterion optimization-based framework, which we cast as a constrained program. The objective of a device is its…

Cache-based approaches stand out as both effective and efficient for adapting vision-language models (VLMs). Nonetheless, the existing cache model overlooks three crucial aspects. 1) Pre-trained VLMs are mainly optimized for image-text…

Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with…

Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE…

Accurate and reliable probability predictions are essential for multi-class supervised learning tasks, where well-calibrated models enable rational decision-making. While isotonic regression has proven effective for binary calibration, its…

Many vision datasets now provide segmentation masks in addition to annotated images to support a wide range of tasks. In this work, we propose Class Activation Map Attention Learning (CAMAL), an efficient and scalable method that utilizes…

There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target…

Transformer-based scientific foundation models are increasingly deployed in high-stakes settings, but current architectures give deterministic outputs and provide limited support for calibrated predictive uncertainty. We propose Stochastic…

Current deep regression models usually learn in a point-wise way that treats each sample as an independent input, neglecting the relative ordering among different data. Consequently, the regression model could neglect the data's…

Accurate sensor calibration is crucial for autonomous systems, yet its uncertainty quantification remains underexplored. We present the first approach to integrate uncertainty awareness into online extrinsic calibration, combining Monte…

Focal Loss has reached incredible popularity as it uses a simple technique to identify and utilize hard examples to achieve better performance on classification. However, this method does not easily generalize outside of classification…

Driver monitoring systems require not just high accuracy but reliable, well-calibrated confidence scores for safety-critical deployment. While direct low-resolution training yields high overall accuracy, it produces poorly calibrated…

Out-of-distribution (OOD) detection is paramount to ensuring the reliability and robustness of learning models in real-world applications. Existing post-hoc OOD detection methods detect OOD samples by leveraging their features and logits…

Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference. We introduce Uncertainty-Guided Inference-Time Selection, a lightweight…

Decentralized learning is crucial in supporting on-device learning over large distributed datasets, eliminating the need for a central server. However, the communication overhead remains a major bottleneck for the practical realization of…

Federated learning has attracted considerable interest for collaborative machine learning in healthcare to leverage separate institutional datasets while maintaining patient privacy. However, additional challenges such as poor calibration…

Reliable confidence estimation for the predictions is important in many safety-critical applications. However, modern deep neural networks are often overconfident for their incorrect predictions. Recently, many calibration methods have been…

While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especially medical images.…

Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a…

AdaBelief, one of the current best optimizers, demonstrates superior generalization ability compared to the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretically appealing in that…