AI Paper Atlas

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

Do Generalised Classifiers really work on Human Drawn Sketches?

Hmrishav Bandyopadhyay, Pinaki Nath Chowdhury, Aneeshan Sain, Subhadeep Koley, Tao Xiang, Ayan Kumar Bhunia, Yi-Zhe Song

ECCV 2024 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 2 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 sketch-specific prompt learning on CLIP (Ours) instead of MaPLeCLIP-based sketch classifier · Edgemaps, TU-Berlin, QuickDraw few-shottop-1 accuracy (%): average margin of 6.66% over MaPLeImproved
use deep prompts (depth 9) instead of shallow prompts (depth 1) (ablation)Ours · TU-Berlin seen classestop-1 accuracy (%): 66.87 -> 76.96Improved
add Meta-Net for instance-conditioned prompts (ablation)Ours · TU-Berlin unseen classestop-1 accuracy (%): 54.19 -> 60.51Improved
add raster-to-vector auxiliary loss (ablation)Ours · TU-Berlin seen classestop-1 accuracy (%): 73.70 -> 76.96Improved
add abstraction codebook vectors and mixup (ablation)Ours · TU-Berlin seen classestop-1 accuracy (%): 73.09 -> 76.96Improved
add abstraction-mixup augmentation (ablation)Ours · TU-Berlin seen classestop-1 accuracy (%): 71.36 -> 76.96Improved
add abstraction mixup on unseen classes (ablation)Ours · TU-Berlin unseen classestop-1 accuracy (%): 60.00 -> 60.51No clear effect
use 5 context tokens instead of 20 (ablation)Ours · TU-Berlin unseen classestop-1 accuracy (%): 55.94 -> 60.51Improved
use CLIP-based methods instead of non-CLIP sketch baselines for unseen classeszero-shot sketch recognition · TU-Berlin unseen classestop-1 accuracy (%): ResNet 1.82 -> CLIP-Z 47.71Improved

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