AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Bayesian Embeddings for Few-Shot Open World Recognition

John Willes, James Harrison, Ali Harakeh, Chelsea Finn, Marco Pavone, Steven L. Waslander

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 29 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 adaptation loss (ablation)SC-FLOWR · TieredImageNet small-contextH-measure: 11.94 -> 13.29Improved
add test-time fine-tuning on top of adaptation loss (ablation)SC-FLOWR · TieredImageNet small-contextH-measure: 13.29 -> 15.04Improved
add test-time fine-tuning on top of adaptation loss (ablation)SC-FLOWR · TieredImageNet small-contextaccuracy: 48.16 -> 51.64Improved
add adaptation loss (ablation)SC-FLOWR · TieredImageNet small-contextaccuracy: 46.24 -> 48.16Improved
use CRP class prior instead of uniform (ablation)SC-FLOWR · TieredImageNet small-contextH-measure: 13.54 -> 15.04Improved
use CRP class prior instead of uniform (ablation)SC-FLOWR · TieredImageNet small-contextincremental accuracy: 41.92 -> 39.39Hurt
add trace regularization beta=0.1 in pre-training (ablation)Sup-E pre-training · MiniImageNet 64-way valaccuracy: 42.26 -> 44.44Improved
trace regularization beta=0.01 instead of none (ablation)Sup-E pre-training · MiniImageNet 64-way valaccuracy: 42.26 -> 42.34No clear effect
use embedding pre-training (Sup-E) instead of FC head (Sup-FC)SC-FLOWR · TieredImageNet small-contextH-measure: 13.31 -> 15.04Improved
use embedding pre-training (Sup-E) instead of FC head (Sup-FC)NCM · MiniImageNet small-contextaccuracy: 37.88 -> 27.49Hurt
use H-measure instead of AUROC to compare PEELER and EVMPEELER vs EVM · TieredImageNet small-contextmetric discrimination: AUROC 53.24 vs 54.96; H-measure 1.00 vs 2.36Improved
SC-FLOWR vs best baselineSC-FLOWR · TieredImageNet small-contextH-measure: 2.36 -> 15.04Improved

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