Search Results for author:
Found 8 papers, 3 papers with code
Affinity and Diversity: Quantifying Mechanisms of Data Augmentation
Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood.
Tradeoffs in Data Augmentation: An Empirical Study
Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood.
Robust fine-tuning of zero-shot models
Compared to standard fine-tuning, WiSE-FT provides large accuracy improvements under distribution shift, while preserving high accuracy on the target distribution.
Ranked #12 on
Image Classification
on ObjectNet
(using extra training data)
Spectral Bias in Practice: The Role of Function Frequency in Generalization
We also explore the connections between function frequency and image frequency and find that spectral bias is sensitive to the low frequencies prevalent in natural images.
No One Representation to Rule Them All: Overlapping Features of Training Methods
Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions.
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-out validation set, discarding the remainder.
Ranked #1 on
Image Classification
on ImageNet V2
(using extra training data)
When does dough become a bagel? Analyzing the remaining mistakes on ImageNet
To help contextualize progress on ImageNet and provide a more meaningful evaluation for today's state-of-the-art models, we manually review and categorize every remaining mistake that a few top models make in order to provide insight into the long-tail of errors on one of the most benchmarked datasets in computer vision.
Queer In AI: A Case Study in Community-Led Participatory AI
We present Queer in AI as a case study for community-led participatory design in AI.
