AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning

Yang Shu, Zhangjie Cao, Jinghan Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long

TPAMI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 15 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 self-distillation regularization R (ablation)Omni-Training (pre+meta+joint losses) · mini-ImageNet 5-shotaccuracy (%): 80.79 -> 81.26Improved
add self-distillation regularization R (ablation)Omni-Training (pre+meta+joint losses) · CUB 5-shotaccuracy (%): 88.54 -> 91.09Improved
add self-distillation regularization R (ablation)Omni-Training (pre+meta+joint losses) · mini-ImageNet->CUB 5-shotaccuracy (%): 70.12 -> 71.30Improved
add joint loss L_joint (ablation)Omni-Training (pre+meta losses) · mini-ImageNet 5-shotaccuracy (%): 78.12 -> 80.79Improved
add joint loss L_joint (ablation)Omni-Training (pre+meta losses) · CUB 5-shotaccuracy (%): 87.34 -> 88.54Improved
add joint loss L_joint (ablation)Omni-Training (pre+meta losses) · mini-ImageNet->CUB 5-shotaccuracy (%): 69.66 -> 70.12Improved
add meta-training loss to pre-training loss (ablation)Omni-Net · mini-ImageNet->CUB 5-shotaccuracy (%): 65.57 -> 69.66Improved
add extra 1x1 conv parameters only (ProtoNet*) (ablation)ProtoNet ResNet-18 · mini-ImageNet 5-shotaccuracy (%): 73.68 -> 73.44No clear effect
use Omni-Net tri-flow instead of just enlarging model (ablation)ProtoNet* ResNet-18 · mini-ImageNet 5-shotaccuracy (%): 73.44 -> 81.26Improved
replace FT-GNN with OT-GNN in Multi-domainFT-GNN · Multi-domain CUB 5-shot (train on mini-ImageNet)accuracy (%): 66.98 -> 70.24Improved
turn all ResNet blocks into Omni-Layers instead of sharing early blocks (ablation)Omni-Net · CUB 5-shotaccuracy (%)Improved
remove self-distillation (lambda=0) (ablation)Omni-Training · mini-ImageNet 1-shotaccuracy (%)Hurt

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