Search Results for author:
Found 6 papers, 4 papers with code
Fake it till you make it: Learning transferable representations from synthetic ImageNet clones
We show that with minimal and class-agnostic prompt engineering, ImageNet clones are able to close a large part of the gap between models produced by synthetic images and models trained with real images, for the several standard classification benchmarks that we consider in this study.
No Reason for No Supervision: Improved Generalization in Supervised Models
We consider the problem of training a deep neural network on a given classification task, e. g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other (future) transfer tasks.
Concept Generalization in Visual Representation Learning
In this paper, we argue that the semantic relationships between seen and unseen concepts affect generalization performance and propose ImageNet-CoG, a novel benchmark on the ImageNet-21K (IN-21K) dataset that enables measuring concept generalization in a principled way.
Hard Negative Mixing for Contrastive Learning
Based on these observations, and motivated by the success of data mixing, we propose hard negative mixing strategies at the feature level, that can be computed on-the-fly with a minimal computational overhead.
Learning Visual Representations with Caption Annotations
Starting from the observation that captioned images are easily crawlable, we argue that this overlooked source of information can be exploited to supervise the training of visual representations.
Gradient Matching Generative Networks for Zero-Shot Learning
In contrast, we propose a generative model that can naturally learn from unsupervised examples, and synthesize training examples for unseen classes purely based on their class embeddings, and therefore, reduce the zero-shot learning problem into a supervised classification task.
