AI Paper Atlas

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

Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach

Vimal K B, Saketh Bachu, Tanmay Garg, Niveditha Lakshmi Narasimhan, Raghavan Konuru, Vineeth N Balasubramanian

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 3 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
add the cohesion term W_C to MS-LEEP (ablation)MS-LEEP · Fully-supervised pool avgWeighted Kendall tau: 0.275 -> 0.265 (WKT); 0.221 -> 0.246 (KT); 0.348 -> 0.383 (PCC)Mixed
add the cohesion term W_C to E-LEEP (ablation)E-LEEP · Fully-supervised pool avgWeighted Kendall tau: 0.097 -> 0.301Improved
include the cohesion term W_C alongside domain and task terms (ablation)OSBORN · Fully-supervised pool avgPearson: 0.496 -> 0.552Improved
include the domain term W_D alongside task and cohesion terms (ablation)OSBORN · Fully-supervised pool avgPearson: 0.482 -> 0.552Improved
include the task term W_T alongside domain and cohesion terms (ablation)OSBORN · Fully-supervised pool avgPearson: 0.556 -> 0.552No clear effect
weight W_D more heavily than W_T and W_C (ablation)OSBORN · Caltech101correlationImproved
use Frobenius norm regularizer in OT for self-supervised pool (ablation)OSBORN · Self-supervised pool avgWeighted Kendall tau: 0.328 -> 0.365Improved
use Frobenius norm regularizer in OT for fully-supervised pool (ablation)OSBORN · Fully-supervised pool avgWeighted Kendall tau: 0.540 -> 0.547No clear effect
replace MS-LEEP/E-LEEP with OSBORN for choosing the ensembleensemble selection · StanfordCars self-supervisedaccuracy: 6.056 -> 61.820Improved
replace MS-LEEP/E-LEEP with OSBORN for choosing the ensembleensemble selection · Caltech101 fully-supervisedaccuracy: 68.533 -> 68.533No clear effect
select ensemble greedily with submodular maximization instead of exhaustive search (ablation)OSBORN · Fully-supervised pool (3 targets avg)accuracy: 79.857 -> 76.315Mixed
use ensemble size larger than 3 (ablation)ensemble selection · Oxford-IIIT Petstest accuracyNo clear effect

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