5 papers
On the Relaxation of Conditional Independence Assumption for Image Segmentation
Zixun Wang, Ben Dai
In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation metrics without modifying model…
EnfoPath: Energy-Informed Analysis of Generative Trajectories in Flow Matching
Ziyun Li, Ben Dai, Huancheng Hu +2
Flow-based generative models synthesize data by integrating a learned velocity field from a reference distribution to the target data distribution. Prior work has focused on endpoi…
RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation
Zixun Wang, Ben Dai
Semantic segmentation labels each pixel in an image with its corresponding class, and is typically evaluated using the Intersection over Union (IoU) and Dice metrics to quantify th…
EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
Ben Dai
Empirical risk minimization (ERM) with a computationally feasible surrogate loss is a widely accepted approach for classification. Notably, the convexity and calibration (CC) prope…
ImbaGCD: Imbalanced Generalized Category Discovery
Ziyun Li, Ben Dai, Furkan Simsek +2
Generalized class discovery (GCD) aims to infer known and unknown categories in an unlabeled dataset leveraging prior knowledge of a labeled set comprising known classes. Existing…