Related papers: A Boundary-Metric Evaluation Protocol for Whiteboa…

Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions…

Deep neural networks for medical image segmentation often produce overconfident results misaligned with empirical observations. Such miscalibration, challenges their clinical translation. We propose to use marginal L1 average calibration…

Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilizing large amounts of unlabeled data with limited labeled samples. Existing methods often suffer from coupling, where over-reliance on initial…

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

Data-efficient image classification using deep neural networks in settings, where only small amounts of labeled data are available, has been an active research area in the recent past. However, an objective comparison between published…

Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…

Medical experts often manually segment images to obtain diagnostic statistics and discard the resulting annotations. We aim to train segmentation models to alleviate this burden, but constrained to the retained summary statistics (e.g., the…

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

This research addresses the challenges of handling unbalanced datasets for binary classification tasks. In such scenarios, standard evaluation metrics are often biased by the disproportionate representation of the minority class. Conducting…

Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to…

Class imbalance is a fundamental challenge in medical image segmentation, where frequent classes typically dominate training at the expense of rare classes. Loss-based approaches mitigate imbalance by reweighting the per-pixel loss within…

The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal…

Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However,…

The field of imbalanced self-supervised learning, especially in the context of tabular data, has not been extensively studied. Existing research has predominantly focused on image datasets. This paper aims to fill this gap by examining the…

Incorporating boundaries of the imaging object as a priori information to imaging algorithms can significantly improve the performance of electromagnetic medical imaging systems. To avoid overly complicating the system by using different…

Class imbalance is a pervasive issue among classification models including deep learning, whose capacity to extract task-specific features is affected in imbalanced settings. However, the challenges of handling imbalance among a large…

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned models on worst-group…

The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations.…

Evaluating rare-event forecasts is challenging because standard metrics collapse as event prevalence declines. Measures such as F1-score, AUPRC, MCC, and accuracy induce degenerate thresholds -- converging to zero or one -- and their values…

Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However,…