A step towards understanding why classification helps regression
A number of computer vision deep regression approaches report improved results when
adding a classification loss to the regression loss. Here, we explore why this is useful in …
adding a classification loss to the regression loss. Here, we explore why this is useful in …
Improving deep regression with ordinal entropy
In computer vision, it is often observed that formulating regression problems as a
classification task often yields better performance. We investigate this curious phenomenon …
classification task often yields better performance. We investigate this curious phenomenon …
Rank-n-contrast: learning continuous representations for regression
Deep regression models typically learn in an end-to-end fashion without explicitly
emphasizing a regression-aware representation. Consequently, the learned representations …
emphasizing a regression-aware representation. Consequently, the learned representations …
Semi-supervised graph imbalanced regression
Data imbalance is easily found in annotated data when the observations of certain
continuous label values are difficult to collect for regression tasks. When they come to …
continuous label values are difficult to collect for regression tasks. When they come to …
Variational imbalanced regression: Fair uncertainty quantification via probabilistic smoothing
Existing regression models tend to fall short in both accuracy and uncertainty estimation
when the label distribution is imbalanced. In this paper, we propose a probabilistic deep …
when the label distribution is imbalanced. In this paper, we propose a probabilistic deep …
Continual learning in predictive autoscaling
Predictive Autoscaling is used to forecast the workloads of servers and prepare the
resources in advance to ensure service level objectives (SLOs) in dynamic cloud …
resources in advance to ensure service level objectives (SLOs) in dynamic cloud …
Conr: Contrastive regularizer for deep imbalanced regression
Imbalanced distributions are ubiquitous in real-world data. They create constraints on Deep
Neural Networks to represent the minority labels and avoid bias towards majority labels. The …
Neural Networks to represent the minority labels and avoid bias towards majority labels. The …
Interpretable cascading mixture-of-experts for urban traffic congestion prediction
Rapid urbanization has significantly escalated traffic congestion, underscoring the need for
advanced congestion prediction services to bolster intelligent transportation systems. As one …
advanced congestion prediction services to bolster intelligent transportation systems. As one …
Deep Imbalanced Regression via Hierarchical Classification Adjustment
Regression tasks in computer vision such as age estimation or counting are often formulated
into classification by quantizing the target space into classes. Yet real-world data is often …
into classification by quantizing the target space into classes. Yet real-world data is often …
OTFPF: Optimal transport based feature pyramid fusion network for brain age estimation
Deep neural networks have shown promise in predicting the chronological age of a healthy
brain using T1-weighted magnetic resonance images (T1 MRIs). This predicted brain age …
brain using T1-weighted magnetic resonance images (T1 MRIs). This predicted brain age …