AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SketchAA: Abstract Representation for Abstract Sketches

Lan Yang, Kaiyue Pang, Honggang Zhang, Yi-Zhe Song

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 26 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 learnable graph aggregator instead of mean pooling (ablation)Ours · QuickDraw recognitiontop-1 accuracy: 77.41% -> 81.51%Improved
use learnable graph aggregator instead of max pooling (ablation)Ours · QuickDraw recognitiontop-1 accuracy: 77.80% -> 81.51%Improved
use learnable graph aggregator instead of concatenation (ablation)Ours · QuickDraw recognitiontop-1 accuracy: 78.22% -> 81.51%Improved
use graph aggregator instead of relational critic (ablation)Ours · QuickDraw recognitiontop-1 accuracy: 80.42% -> 81.51%Improved
use graph aggregator instead of LSTM extrapolation (ablation)Ours · QuickDraw recognitiontop-1 accuracy: 80.91% -> 81.51%Improved
use graph aggregator instead of mean pooling (ablation)Ours · QMUL Chair V2Acc@1: 43.24 -> 52.89Improved
use graph aggregator instead of mean pooling (ablation)Ours · QMUL Shoe V2Acc@1: 29.13 -> 32.33Improved
fine-tune plain ResNet-50 instead of vector-sequence methodsResNet-50 · QuickDraw recognitiontop-1 accuracy: 78.76% vs 77.31% (SketchGCN), 78.34% (SketchFormer)Improved
raise abstraction levels from q=1 to q=2 (ablation)Ours · QuickDraw recognitiontop-1 accuracy: 80.04% -> 81.51%Improved
raise abstraction levels from q=2 to q=3 (ablation)Ours · QMUL Chair V2Acc@1: 47.64% -> 52.89%Improved
raise abstraction levels from q=3 to q=4 (ablation)Ours · QMUL Shoe V2Acc@1: 32.33% -> 31.52%Hurt
raise input size to 512x512 with q=4 instead of q=2 (ablation)Ours · QuickDraw recognitiontop-1 accuracy: 81.89% -> 82.05%Improved

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