AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

tSF: Transformer-Based Semantic Filter for Few-Shot Learning

Jinxiang Lai, Siqian Yang, Wenlong Liu, Yi Zeng, Zhongyi Huang, Wenlong Wu, Jun Liu, Bin-Bin Gao, Chengjie Wang

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection

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 tSF neck to PatchProtoPatchProto (ResNet-12) · miniImageNet 5-way 1-shotaccuracy: 68.46 -> 69.74Improved
add tSF neck to PatchProtoPatchProto (WRN-28) · tieredImageNet 5-way 5-shotaccuracy: 86.85 -> 88.05Improved
add tSF neck to baseline without neck (ablation)PatchProto (ResNet-12, no rotation) · miniImageNet 5-way 1-shotaccuracy: 67.47 -> 68.37Improved
add standard self-attention transformer neck (ablation)PatchProto (ResNet-12, no neck) · miniImageNet 5-way 1-shotaccuracy: 67.47 -> 63.25Hurt
add DETR-style decoder neck (ablation)PatchProto (ResNet-12, no neck) · miniImageNet 5-way 1-shotaccuracy: 67.47 -> 63.55Hurt
use V=theta instead of K=V=theta (tSF-V variant) (ablation)tSF · miniImageNet 5-way 1-shotaccuracy: 68.37 -> 61.84Hurt
use K=V=theta rather than only K=theta (tSF-K variant) (ablation)tSF · miniImageNet 5-way 1-shotaccuracy: 64.73 -> 68.37Improved
add learnable projections W_Q, W_K, W_V to tSF (ablation)tSF · miniImageNet 5-way 1-shotaccuracy: 68.37 -> 68.27No clear effect
increase tSF attention heads from 1 to 4 (ablation)tSF · miniImageNet 5-way 1-shotaccuracy: 68.37 -> 68.60No clear effect
vary dimension n of theta from 1 to 1024 (ablation)tSF · miniImageNet 5-way (1-shot and 5-shot)accuracy: within 0.5%No clear effect
add global classification auxiliary task (ablation)PatchProto+tSF (ResNet-12) · miniImageNet 5-way 1-shotaccuracy: 62.76 -> 68.60Improved
add rotation classification auxiliary task (ablation)PatchProto+tSF (ResNet-12) · miniImageNet 5-way 1-shotaccuracy: 62.76 -> 65.57Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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