相关论文: Model Patching: Closing the Subgroup Performance G…

Machine learning models are typically deployed in a test setting that differs from the training setting, potentially leading to decreased model performance because of domain shift. If we could estimate the performance that a pre-trained…

In this work, we propose data augmentation via pairwise mixup across subgroups to improve group fairness. Many real-world applications of machine learning systems exhibit biases across certain groups due to under-representation or training…

Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN was recently proposed for this problem, but critically…

Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples. Given the inherent diversity of tasks arising in existing benchmarks, recent methods use…

Deep learning models (DLMs) frequently achieve accurate segmentation and classification of tumors from medical images. However, DLMs lacking feedback on their image segmentation mechanisms, such as Dice coefficients and confidence in their…

Automatic skin lesion classification from dermoscopy images is important for the early diagnosis of skin diseases such as melanoma. Class imbalance in skin lesion datasets, notably the defects in the representation of malignant(cancerous)…

Skin image datasets often suffer from imbalanced data distribution, exacerbating the difficulty of computer-aided skin disease diagnosis. Some recent works exploit supervised contrastive learning (SCL) for this long-tailed challenge.…

Deep neural networks have demonstrated promising performance on image recognition tasks. However, they may heavily rely on confounding factors, using irrelevant artifacts or bias within the dataset as the cue to improve performance. When a…

Skin cancer is a life-threatening disease where early detection significantly improves patient outcomes. Automated diagnosis from dermoscopic images is challenging due to high intra-class variability and subtle inter-class differences. Many…

Large capacity deep learning models are often prone to a high generalization gap when trained with a limited amount of labeled training data. A recent class of methods to address this problem uses various ways to construct a new training…

Software defect prediction models can assist software testing initiatives by prioritizing testing error-prone modules. In recent years, in addition to the traditional defect prediction model approach of predicting defects from class,…

Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieved great success. However, existing automated DA methods…

Skin cancer is a highly dangerous type of cancer that requires an accurate diagnosis from experienced physicians. To help physicians diagnose skin cancer more efficiently, a computer-aided diagnosis (CAD) system can be very helpful. In this…

Uncertainty quantification in automated image analysis is highly desired in many applications. Typically, machine learning models in classification or segmentation are only developed to provide binary answers; however, quantifying the…

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…

Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing-based augmentation…

In this work, we explore the limitations of combining models by averaging intermediate features, referred to as model merging, and propose a new direction for achieving collective model intelligence through what we call compatible…

Foundation models for segmentation such as the Segment Anything Model (SAM) family exhibit strong zero-shot performance, but remain vulnerable in shifted or limited-knowledge domains. This work investigates whether uncertainty…

The integration of machine learning models in various real-world applications is becoming more prevalent to assist humans in their daily decision-making tasks as a result of recent advancements in this field. However, it has been discovered…

Understanding how a complex machine learning model makes a classification decision is essential for its acceptance in sensitive areas such as health care. Towards this end, we present PatchNet, a method that provides the features indicative…