Deep Learning
Wavelet Feature Maps Compression for Image-to-Image CNNs Shahaf E. Finder
While aggressive quantization (i.e., less than 4-bits) performs well for classification, it may cause severe performance degradation in image-to-image tasks such as semantic segmentation and depth estimation.
Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection Fan Wang 1,2 Adams Wai-Kin Kong 1 1
Kendall's rank correlation is a key performance index for attribution protection.
Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome
Data augmentation plays a key role in modern machine learning pipelines.
Learning to Mutate with Hypergradient Guided Population
Computing the gradient of model hyperparameters, i.e., hypergradient, enables a
MVP-N: A Dataset and Benchmark for Real-World Multi-View Object Classification
The fine-grained categorization of objects naturally generates multi-view label noise owing to the inter-class view similarity, allowing the study of learning from noisy labels in the multi-view case.
