AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

FastFill: Efficient Compatible Model Update

Florian Jaeckle, Fartash Faghri, Ali Farhadi, Oncel Tuzel, Hadi Pouransari

ICLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 0 citations (OpenAlex)

Read the paper

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
Replace FCT with FastFill’s alignment and uncertainty-based partial-backfilling policyCompatible embedding update · ImageNet-1kaverage mAP: 40.47 -> 44.84Improved
Replace FCT with FastFill’s alignment and uncertainty-based partial-backfilling policyCompatible embedding update · Places-365average mAP: 16.81 -> 19.48Improved
Replace FCT with FastFill’s alignment and uncertainty-based partial-backfilling policyCompatible embedding update · VGGFace2average mAP: 70.26 -> 71.57Improved
Add the discriminative objective to L2 alignment (ablation)FastFill alignment; random ordering · ImageNet-1kaverage mAP: 40.47 -> 41.95Improved
Use discriminative loss alone instead of L2 alignment (ablation)FastFill alignment; random ordering · ImageNet-1kaverage mAP: 40.47 -> 39.45Hurt
Add uncertainty estimation while keeping random backfilling and L2 alignment (ablation)FastFill · ImageNet-1kaverage mAP: 40.47 -> 40.08No clear effect
Use predicted uncertainty to order backfilling rather than random order (ablation)FastFill with L2 + discriminative loss and uncertainty · ImageNet-1kaverage mAP: 42.05 -> 44.84Improved
Use discriminative loss alone with uncertainty-based ordering instead of the combined alignment loss (ablation)FastFill · ImageNet-1kaverage mAP: 44.84 -> 27.59Hurt
Use Bayesian uncertainty instead of entropy uncertainty (ablation)FastFill backfilling policy · Places-365average mAP: 18.6 -> 19.48Improved
Use Bayesian uncertainty instead of entropy-based uncertainty (ablation)FastFill backfilling policy · ImageNet-250 to ImageNet-500, disjoint classes [500:]average top1: 15.22 -> 17.9Improved
Use Bayesian uncertainty instead of margin-confidence uncertainty (ablation)FastFill backfilling policy · ImageNet-250 to ImageNet-500, disjoint classes [500:]average top1: 15.17 -> 17.9Improved
Use Bayesian uncertainty instead of least-confidence uncertainty (ablation)FastFill backfilling policy · ImageNet-250 to ImageNet-500, disjoint classes [500:]average top1: 15.18 -> 17.9Improved

Later papers that compared with this method

1 later accepted paper reports FastFill as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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