AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Learning Recourse on Instance Environment to Enhance Prediction Accuracy

Lokesh Nagalapatti, Guntakanti Sai Koushik, Abir De, Sunita Sarawagi

NeurIPS 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 0 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
train classifier with iterative greedy subsetting instead of full data (ablation)RecourseNet classifier f_theta · Shapenet-Largeaccuracy at 100% recourse: 71.93 ± 0.63 -> 77.14 ± 0.63Improved
train classifier with iterative greedy subsetting instead of full data (ablation)RecourseNet classifier f_theta · Shapenet-Smallaccuracy at 100% recourse: 62.97 ± 0.80 -> 74.13 ± 1.10Improved
train classifier with iterative greedy subsetting instead of full data (ablation)RecourseNet classifier f_theta · Speech Commandsaccuracy at 100% recourse: 51.85 ± 1.08 -> 65.76 ± 1.44Improved
train classifier with iterative greedy subsetting instead of full data (ablation)RecourseNet classifier f_theta · Skin-Lesionaccuracy at 100% recourse: 56.42 ± 0.80 -> 68.62 ± 0.90Improved
iterative greedy subsetting instead of one-shot subsetting (ablation)RecourseNet classifier f_theta · Shapenet-Smallaccuracy at 100% recourse: 65.55 ± 1.11 -> 74.13 ± 1.10Improved
one-shot subsetting instead of full data (ablation)classifier f_theta · Shapenet-Largeaccuracy at 100% recourse: 71.93 ± 0.63 -> 72.63 ± 0.54No clear effect
one-shot subsetting instead of full data (ablation)classifier f_theta · Skin-Lesionaccuracy at 100% recourse: 56.42 ± 0.80 -> 60.89 ± 1.11Improved
learned recourse trigger pi using expected gain from f_CF instead of score-based, loss-predictor or random triggers (ablation)RecourseNet · all four datasets, varying budget baccuracy after recourseImproved
random trigger instead of learned trigger (ablation)RecourseNet · all four datasets, varying budget baccuracy after recourseHurt
add f_CF supervision term to recommender objective (7) vs objective (6) without it (ablation)recourse recommender g_phi · Shapenet-Smallrecourse accuracyImproved
add f_CF supervision term to recommender objective (7) vs objective (6) without it (ablation)recourse recommender g_phi · Shapenet-Large and Speech Commandsrecourse accuracyNo clear effect
use full objective (7) with D minus D_delta handling instead of only-phi model (ablation)recourse recommender g_phi · Shapenet-Largerecourse accuracyImproved

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