AI Paper Atlas

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

Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning

Rongkai Ma, Pengfei Fang, Gil Avraham, Yan Zuo, Tianyu Zhu, Tom Drummond, Mehrtash Harandi

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification

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 task-specific kernel to support features (ablation)ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 79.46 -> 81.56Improved
also apply the task-specific kernel to query features (ablation)ProtoNet + task kernel · mini-ImageNet 5-way 5-shotaccuracy: 81.56 -> 82.51Improved
add instance kernel (ablation)ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 79.46 -> 80.81Improved
add instance kernel on top of task-specific kernel (ablation)ProtoNet + task kernel · mini-ImageNet 5-way 5-shotaccuracy: 81.56 -> 81.74Improved
adapt query features with the task-specific kernel (ablation)INSTA-ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 81.74 -> 83.13Improved
use multi-spectral attention instead of global average pooling (ablation)INSTA-ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 82.07 -> 83.13Improved
extract an instance kernel from the query too (ablation)INSTA-ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 83.13 -> 82.24No clear effect
share the dynamic kernel generator between task and instance kernels (ablation)INSTA-ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 81.36 -> 83.13Improved
add residual connection between adapted and original features (ablation)INSTA-ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 80.03 -> 83.13Improved
use 3x3 dynamic kernel instead of 5x5 (ablation)INSTA-ProtoNet · mini-ImageNet 5-way 5-shotaccuracy: 82.43 -> 83.13Improved
add INSTA to ProtoNet (ablation)ProtoNet ResNet-12 · mini-ImageNet 5-way 1-shotaccuracy: 62.29 -> 67.01Improved
add INSTA to DeepEMD (ablation)DeepEMD ResNet-12 · tiered-ImageNet 5-way 5-shotaccuracy: 86.79 -> 88.02Improved

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