Search Results for author:
Found 12 papers, 12 papers with code
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
What additional value does the intermediate generator provide over directly training on relevant parts of the upstream data?
Neural Priming for Sample-Efficient Adaptation
Performing lightweight updates on the recalled data significantly improves accuracy across a variety of distribution shift and transfer learning benchmarks.
DataComp: In search of the next generation of multimodal datasets
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms.
Neural Radiance Field Codebooks
Compositional representations of the world are a promising step towards enabling high-level scene understanding and efficient transfer to downstream tasks.
Matryoshka Representation Learning
The flexibility within the learned Matryoshka Representations offer: (a) up to 14x smaller embedding size for ImageNet-1K classification at the same level of accuracy; (b) up to 14x real-world speed-ups for large-scale retrieval on ImageNet-1K and 4K; and (c) up to 2% accuracy improvements for long-tail few-shot classification, all while being as robust as the original representations.
Ranked #25 on
Image Classification
on ObjectNet
(using extra training data)
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
To avoid the cost of backfilling, BCT modifies training of the new model to make its representations compatible with those of the old model.
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
We further quantitatively measure the quality of our codes by applying it to the efficient image retrieval as well as out-of-distribution (OOD) detection problems.
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent
To better understand this bias, we study the tendency for transformer parameters to grow in magnitude ($\ell_2$ norm) during training, and its implications for the emergent representations within self attention layers.
Supermasks in Superposition
We present the Supermasks in Superposition (SupSup) model, capable of sequentially learning thousands of tasks without catastrophic forgetting.
Soft Threshold Weight Reparameterization for Learnable Sparsity
Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget.
What's Hidden in a Randomly Weighted Neural Network?
Training a neural network is synonymous with learning the values of the weights.
Ranked #968 on
Image Classification
on ImageNet
Improving Shape Deformation in Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change.
