164 citations · 491 across the 15 of their papers we have counts for
16 papers
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
Thomas Hartvigsen, Swami Sankaranarayanan, Hamid Palangi +2
Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted…
Semantic uncertainty intervals for disentangled latent spaces
Swami Sankaranarayanan, Anastasios N. Angelopoulos, Stephen Bates +2
Meaningful uncertainty quantification in computer vision requires reasoning about semantic information -- say, the hair color of the person in a photo or the location of a car on t…
Exploring Visual Prompts for Adapting Large-Scale Models
Hyojin Bahng, Ali Jahanian, Swami Sankaranarayanan +1
We investigate the efficacy of visual prompting to adapt large-scale models in vision. Following the recent approach from prompt tuning and adversarial reprogramming, we learn a si…
Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion
Ryutaro Tanno, Ardavan Saeedi, Swami Sankaranarayanan +2
The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy e…
Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
Rajeev Ranjan, Ankan Bansal, Hongyu Xu +4
In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for…
Improving Network Robustness against Adversarial Attacks with Compact Convolution
Rajeev Ranjan, Swami Sankaranarayanan, Carlos D. Castillo +1
Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by advers…