activity
20192021
most citedRethinking the Hyperparameters for Fine-tuning

63 citations · 89 across the 5 of their papers we have counts for

collaborators

12 papers

cs.CV202110 cited

A linearized framework and a new benchmark for model selection for fine-tuning

Aditya Deshpande, Alessandro Achille, Avinash Ravichandran +6

Fine-tuning from a collection of models pre-trained on different domains (a "model zoo") is emerging as a technique to improve test accuracy in the low-data regime. However, model…

cs.LG20212 cited

Estimating informativeness of samples with Smooth Unique Information

Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini +4

We define a notion of information that an individual sample provides to the training of a neural network, and we specialize it to measure both how much a sample informs the final w…

cs.LG2020

LQF: Linear Quadratic Fine-Tuning

Alessandro Achille, Aditya Golatkar, Avinash Ravichandran +2

Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial c…

cs.LG20206 cited

Predicting Training Time Without Training

Luca Zancato, Alessandro Achille, Avinash Ravichandran +2

We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. To do so, we leverage…

cs.CV202063 cited

Rethinking the Hyperparameters for Fine-tuning

Hao Li, Pratik Chaudhari, Hao Yang +4

Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad…

cs.CV2020

Multi-Task Incremental Learning for Object Detection

Xialei Liu, Hao Yang, Avinash Ravichandran +2

Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementa…