AI Paper Atlas

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

Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition

Siteng Huang, Min Zhang, Yachen Kang, Donglin Wang

AAAI 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 42 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 AGAM to ProtoNetProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 53.01 ± 0.34 -> 75.87 ± 0.29; 71.91 ± 0.22 -> 81.66 ± 0.25Improved
Add AGAM to ProtoNetProtoNet, Conv-4 · SUN 5-way 1-shot and 5-shotaccuracy: 57.76 ± 0.29 -> 65.15 ± 0.31; 79.27 ± 0.19 -> 80.08 ± 0.21Improved
Add human-annotated attributes to AGAM (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 67.35 ± 0.32 -> 75.87 ± 0.29; 77.87 ± 0.19 -> 81.66 ± 0.25Improved
Replace real attributes with all-0 attributes (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 75.87 ± 0.29 -> 63.47 ± 0.35; 81.66 ± 0.25 -> 75.27 ± 0.20Hurt
Swap spatial and channel attention order (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 75.87 ± 0.29 -> 74.22 ± 0.27; 81.66 ± 0.25 -> 79.72 ± 0.26Hurt
Remove average pooling (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 75.87 ± 0.29 -> 66.27 ± 0.29; 81.66 ± 0.25 -> 76.58 ± 0.25Hurt
Remove max pooling (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 75.87 ± 0.29 -> 67.60 ± 0.29; 81.66 ± 0.25 -> 77.09 ± 0.22Hurt
Remove channel-wise attention (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shotaccuracy: 75.87 ± 0.29 -> 54.91 ± 0.36Hurt
Remove spatial-wise attention (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 75.87 ± 0.29 -> 69.66 ± 0.31; 81.66 ± 0.25 -> 76.24 ± 0.27Hurt
Add both channel and spatial attention alignment losses (ablation)AGAM with ProtoNet, Conv-4 · CUB 5-way 1-shot and 5-shotaccuracy: 75.37 ± 0.31 -> 75.87 ± 0.29; 78.92 ± 0.27 -> 81.66 ± 0.25Improved
Use soft margin instead of L1, MSE, or smoothL1 for attention alignment (ablation)AGAM · CUB and SUN 5-way 1-shot and 5-shotaccuracyImproved

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