20 citations · 55 across the 17 of their papers we have counts for
18 papers
Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing
A K Nirala, A Joshi, C Hegde +1
A key benefit of deep vision-language models such as CLIP is that they enable zero-shot open vocabulary classification; the user has the ability to define novel class labels via na…
PriViT: Vision Transformers for Fast Private Inference
Naren Dhyani, Jianqiao Mo, Minsu Cho +4
The Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. However, ViTs are ill-suited for…
Distributionally Robust Classification on a Data Budget
Benjamin Feuer, Ameya Joshi, Minh Pham +1
Real world uses of deep learning require predictable model behavior under distribution shifts. Models such as CLIP show emergent natural distributional robustness comparable to hum…
Identity-Preserving Aging of Face Images via Latent Diffusion Models
Sudipta Banerjee, Govind Mittal, Ameya Joshi +2
The performance of automated face recognition systems is inevitably impacted by the facial aging process. However, high quality datasets of individuals collected over several years…
ZeroForge: Feedforward Text-to-Shape Without 3D Supervision
Kelly O. Marshall, Minh Pham, Ameya Joshi +4
Current state-of-the-art methods for text-to-shape generation either require supervised training using a labeled dataset of pre-defined 3D shapes, or perform expensive inference-ti…
Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos
Md Zahid Hasan, Jiajing Chen, Jiyang Wang +6
Recognizing the activities causing distraction in real-world driving scenarios is critical for ensuring the safety and reliability of both drivers and pedestrians on the roadways.…