Related papers: Is Synthetic Image Augmentation Useful for Imbalan…

Accurate vehicle type recognition underpins intelligent transportation and logistics, but severe class imbalance in public datasets suppresses performance on rare categories. We curate a 16-class corpus (~47k images) by merging Kaggle,…

Anomaly detection focuses on identifying samples that deviate from the norm. Discovering informative representations of normal samples is crucial to detecting anomalies effectively. Recent self-supervised methods have successfully learned…

This work introduces a novel biorthogonal tunable wavelet unit constructed using a lifting scheme that relaxes both the orthogonality and equal filter length constraints, providing greater flexibility in filter design. The proposed unit…

We present a controlled comparison of a convolutional neural network (EfficientNet-B0) and a Vision Transformer (ViT-Base) on SpaceNet under two label-distribution regimes: a naturally imbalanced five-class split and a balanced-resampled…

Large pretrained visual foundation models exhibit impressive general capabilities. However, the extensive prior knowledge inherent in these models can sometimes be a double-edged sword when adapting them to downstream tasks in specific…

Predictive uncertainty-a model's self awareness regarding its accuracy on an input-is key for both building robust models via training interventions and for test-time applications such as selective classification. We propose a novel…

Deep learning based medical image recognition systems often require a substantial amount of training data with expert annotations, which can be expensive and time-consuming to obtain. Recently, synthetic augmentation techniques have been…

Data imbalance in training data often leads to biased predictions from trained models, which in turn causes ethical and social issues. A straightforward solution is to carefully curate training data, but given the enormous scale of modern…

Machine learning offers potential solutions to current issues in industrial systems in areas such as quality control and predictive maintenance, but also faces unique barriers in industrial applications. An ongoing challenge is extreme…

Recent developments in the field of deep learning for 3D data have demonstrated promising potential for end-to-end learning directly from point clouds. However, many real-world point clouds contain a large class im-balance due to the…

Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category…

Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation,…

Classifying imbalanced datasets remains a significant challenge in machine learning, particularly with big data where instances are unevenly distributed among classes, leading to class imbalance issues that impact classifier performance.…

Pathology computing has dramatically improved pathologists' workflow and diagnostic decision-making processes. Although computer-aided diagnostic systems have shown considerable value in whole slide image (WSI) analysis, the problem of…

In recent years, performance on existing anomaly detection benchmarks like MVTec AD and VisA has started to saturate in terms of segmentation AU-PRO, with state-of-the-art models often competing in the range of less than one percentage…

Transfer learning has become an essential part of medical imaging classification algorithms, often leveraging ImageNet weights. The domain shift from natural to medical images has prompted alternatives such as RadImageNet, often showing…

Class imbalance poses a challenge for developing unbiased, accurate predictive models. In particular, in image segmentation neural networks may overfit to the foreground samples from small structures, which are often heavily…

The accuracy and fairness of perception systems in autonomous driving are essential, especially for vulnerable road users such as cyclists, pedestrians, and motorcyclists who face significant risks in urban driving environments. While…

This is the submission for mitosis detection in the context of the MIDOG 2021 challenge. It is based on the two-stage objection model Faster RCNN as well as DenseNet as a backbone for the neural network architecture. It achieves a F1-score…

Publicly available diabetic retinopathy (DR) datasets are imbalanced, containing limited numbers of images with DR. This imbalance contributes to overfitting when training machine learning classifiers. The impact of this imbalance is…