AI Paper Atlas

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

Differentiable Meta-Learning Model for Few-Shot Semantic Segmentation

Pinzhuo Tian, Zhangkai Wu, Lei Qi, Lei Wang, Yinghuan Shi, Yang Gao

AAAI 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 96 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
Use pixel classification with a differentiable linear base learner for multi-object segmentationMetaSegNet · PASCAL-5^2, 2-way 5-shotMean IoU (%): 42.6 -> 43.3Improved
Use MetaSegNet instead of the strongest listed baselineCOCO, 2-way few-shot segmentation · COCO, 2-way 1-shotMean IoU (%): 29.3 -> 33.2Improved
Increase support examples from 1-shot to 10-shotMetaSegNet · COCO, 2-way segmentationMean IoU (%): 33.2 -> 38.3Improved
Use MetaSegNet with miniImageNet pretraining instead of OSLSMPASCAL-5^i, 1-way 5-shot · PASCAL-5^iMean IoU (%): 61.5 -> 59.5Hurt
Add episodic meta-training rather than fine-tuning (ablation)Few-shot segmentation on PASCAL-5^i_val · PASCAL-5^i_val, 2-way 1-shotMean IoU (%): 27.28 -> 35.00Improved
Add ridge regression as the linear base learner instead of a 1×1 convolution (ablation)MetaSegNet-NG · PASCAL-5^i_val, 2-way 1-shotMean IoU (%): 35.00 -> 37.75Improved
Add the global context branch (ablation)MetaSegNet · PASCAL-5^i_val, 2-way 1-shotMean IoU (%): 37.75 -> 38.92Improved
Add ridge regression as the linear base learner instead of a 1×1 convolution (ablation)MetaSegNet-NG · PASCAL-5^i_val, 2-way 5-shotMean IoU (%): 36.04 -> 48.34Improved
Add the global context branch (ablation)MetaSegNet · PASCAL-5^i_val, 2-way 5-shotMean IoU (%): 48.34 -> 49.44Improved
Increase support examples from 1-shot to 5-shot (ablation)MetaSegNet · PASCAL-5^i_val, 2-way segmentationMean IoU (%)Improved
Train MetaSegNet from scratch rather than pretraining on miniImageNetMetaSegNet · PASCAL-5^i, 1-way 5-shotMean IoU (%): 59.5 -> 53.4Hurt

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