AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Debiasing surgeon: fantastic weights and how to find them

Remi Nahon, Ivan Luiz De Moura Matos, Van-Tam Nguyen, Enzo Tartaglione

ECCV 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
prune the vanilla-trained model with FFW without fine-tuningSimpleConvNet · Biased MNIST rho=0.99task accuracy (%): 88.46 -> 97.79Improved
prune the vanilla-trained model with FFW without fine-tuningSimpleConvNet · Biased MNIST rho=0.999task accuracy (%): 10.02 -> 22.29No clear effect
prune with FFW on Corrupted CIFAR10ResNet-18 · Corrupted CIFAR10 rho=0.995task accuracy (%): 20.50 -> 51.57Improved
prune with FFW on CelebA BlondHairResNet-18 · CelebA BlondHairtask accuracy (%): 80.42 -> 87.08Improved
prune with FFW on Multi-Color MNIST3-layer MLP · Multi-Color MNIST averageaverage task accuracy (%): 58.9 -> 36.37Hurt
prune with FFW on Multi-Color MNIST worst subgroup3-layer MLP · Multi-Color MNIST conflicting both sidestask accuracy (%): 7.68 -> 35.85Improved
increase regularization coefficient gamma to 50 or above (ablation)FFW · Biased MNIST rho=0.99task accuracy (%): 97.79 -> 93.68 (gamma 50), 23.31 (gamma 200)Hurt
use FFW instead of magnitude pruning at 90% sparsity (ablation)SimpleConvNet · Biased MNIST rho=0.99task accuracy (%): 31.14 -> 97.79Improved
extract sub-network from vanilla model trained for more epochs (ablation)FFW · Biased MNIST rho=0.99task accuracy (%): 12.42 -> 97.96 (1 -> 40 epochs)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy