decision boundaries
Decision boundaries refer to the boundaries that separate different classes in the feature space of a classification model. They determine how the model categorizes inputs, and their shape can influence generalization capabilities.
- Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
- Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
- Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
- Exploring and Leveraging Class Vectors for Classifier Editing
- How to Learn a Star: Binary Classification with Starshaped Polyhedral Sets
- Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
- LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
- Learning Multi-Source and Robust Representations for Continual Learning
- Long-Tailed Recognition via Information-Preservable Two-Stage Learning
- OOD Detection with Relative Angles
- OSTAR: Optimized Statistical Text-classifier with Adversarial Resistance
- Variational Supervised Contrastive Learning
- Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation