Chih-Hui Ho

9

Papers

34

Total Citations

Papers (9)

Long-Tailed Anomaly Detection with Learnable Class Names

ProTeCt: Prompt Tuning for Taxonomic Open Set Classification

Catastrophic Child's Play: Easy to Perform, Hard to Defend Adversarial Attacks

PIEs: Pose Invariant Embeddings

Exploit Clues From Views: Self-Supervised and Regularized Learning for Multiview Object Recognition

Toward Unsupervised Realistic Visual Question Answering

Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier

Contrastive Learning with Adversarial Examples

DISCO: Adversarial Defense with Local Implicit Functions