9 citations · 18 across the 9 of their papers we have counts for
4 papers · 1 filter
IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adaptation
Yuan Yin, Shashanka Venkataramanan, Tuan-Hung Vu +2
Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, reduce adaptation cost by injecting low-rank updates into pretrained weights. However, LoRA's down-projection is rando…
Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples
Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg +1
Mixup refers to interpolation-based data augmentation, originally motivated as a way to go beyond empirical risk minimization (ERM). Its extensions mostly focus on the definition o…
Teach me how to Interpolate a Myriad of Embeddings
Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg +1
Mixup refers to interpolation-based data augmentation, originally motivated as a way to go beyond empirical risk minimization (ERM). Yet, its extensions focus on the definition of…
It Takes Two to Tango: Mixup for Deep Metric Learning
Shashanka Venkataramanan, Bill Psomas, Ewa Kijak +3
Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pus…