Search Results for author:
Found 13 papers, 6 papers with code
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
Battle of the Backbones (BoB) makes this choice easier by benchmarking a diverse suite of pretrained models, including vision-language models, those trained via self-supervised learning, and the Stable Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more.
K-SAM: Sharpness-Aware Minimization at the Speed of SGD
Sharpness-Aware Minimization (SAM) has recently emerged as a robust technique for improving the accuracy of deep neural networks.
Contrastive Learning is Just Meta-Learning
Contrastive learning has recently taken off as a paradigm for learning from unlabeled data.
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision.
Ranked #137 on
Image Classification
on CIFAR-10
WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic
Low-precision neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity.
Data Augmentation for Meta-Learning
Conventional image classifiers are trained by randomly sampling mini-batches of images.
WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic
Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity.
Certified Defenses for Adversarial Patches
Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems.
Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical robustness.
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
In doing so, we introduce and verify several hypotheses for why meta-learned models perform better.
WITCHcraft: Efficient PGD attacks with random step size
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points.
Improved Training of Certifiably Robust Models
Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical (PGD) robustness.
Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
This procedure can greatly compensate the quantization error and thus yield better accuracy for low-bit DNNs.
