AI Paper Atlas

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

Task-Aware Part Mining Network for Few-Shot Learning

Jiamin Wu, Tianzhu Zhang, Yongdong Zhang, Feng Wu

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot · 79 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 generic part filters (ablation)ProtoNet · miniImageNet 5-way 1-shotaccuracy: 60.47 -> 64.11Improved
add task-aware part filters (ablation)ProtoNet · miniImageNet 5-way 1-shotaccuracy: 60.47 -> 65.94Improved
use task-aware part filters instead of generic part filters (ablation)ProtoNet + part filters · miniImageNet 5-way 1-shotaccuracy: 64.11 -> 65.94Improved
add diversity loss Ldiv (ablation)ProtoNet + TAPF · miniImageNet 5-way 5-shotaccuracy: 81.47 -> 82.84Improved
add diversity loss Ldiv (ablation)ProtoNet + TAPF · miniImageNet 5-way 1-shotaccuracy: 65.94 -> 66.53Improved
add adaptive importance generator Ga (ablation)ProtoNet + TAPF · miniImageNet 5-way 5-shotaccuracy: 81.47 -> 82.39Improved
add adaptive importance generator Ga (ablation)ProtoNet + TAPF · miniImageNet 5-way 1-shotaccuracy: 65.94 -> 66.83Improved
add both Ga and Ldiv (full TPMN) (ablation)ProtoNet + TAPF · miniImageNet 5-way 5-shotaccuracy: 81.47 -> 83.44Improved
vary number of local parts Nf (ablation)TPMN · miniImageNet 5-way 1-shotaccuracy: best at Nf = 15 (1-shot), Nf = 20 (5-shot)Mixed
replace ProtoNet global representation with TPMN local part representationProtoNet · miniImageNet 5-way 1-shotaccuracy: +7.17%Improved
replace ProtoNet global representation with TPMN local part representationProtoNet · miniImageNet 5-way 5-shotaccuracy: +3.97%Improved
use TPMN instead of FEAT under cross-domain transferFEAT · miniImageNet to CUB 5-way 1-shotaccuracy: 50.67 -> 52.83Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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