Search Results for author:
Found 13 papers, 7 papers with code
Aligning and Projecting Images to Class-conditional Generative Networks
We present a method for projecting an input image into the space of a class-conditional generative neural network.
Scalable Optimization in the Modular Norm
When ramping up the width of a single layer, graceful scaling of training has been linked to the need to normalize the weights and their updates in the "natural norm" particular to that layer.
The Platonic Representation Hypothesis
We argue that representations in AI models, particularly deep networks, are converging.
Training Neural Networks from Scratch with Parallel Low-Rank Adapters
The scalability of deep learning models is fundamentally limited by computing resources, memory, and communication.
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
We identify the factors that contribute to this issue, including the codebook gradient sparsity and the asymmetric nature of the commitment loss, which leads to misaligned code-vector assignments.
Totems: Physical Objects for Verifying Visual Integrity
We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene.
Learning to Ground Multi-Agent Communication with Autoencoders
Communication requires having a common language, a lingua franca, between agents.
The Low-Rank Simplicity Bias in Deep Networks
We show empirically that our claim holds true on finite width linear and non-linear models on practical learning paradigms and show that on natural data, these are often the solutions that generalize well.
Transforming and Projecting Images into Class-conditional Generative Networks
We present a method for projecting an input image into the space of a class-conditional generative neural network.
Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks
We propose feedback adversarial learning (FAL) framework that can improve existing generative adversarial networks by leveraging spatial feedback from the discriminator.
Multi-view to Novel view: Synthesizing Novel Views with Self-Learned Confidence
We address the task of multi-view novel view synthesis, where we are interested in synthesizing a target image with an arbitrary camera pose from given source images.
Ranked #1 on
Novel View Synthesis
on Synthia Novel View Synthesis
Fighting Fake News: Image Splice Detection via Learned Self-Consistency
In this paper, we propose a learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs.
What makes ImageNet good for transfer learning?
Which is better: more classes or more examples per class?
