AI Paper Atlas

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

MRSP: Learn Multi-Representations of Single Primitive for Compositional Zero-Shot Learning

Dongyao Jiang, Hui Chen, Haodong Jing, Yongqiang Ma, Nanning Zheng

ECCV 2024 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 5 citations (OpenAlex)

Read the paper

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
learn multiple representations per primitive (state, object, composition nodes) instead of one (ablation)MRSP with cross-attention · MIT-States closed-worldAUC: 12.6 -> 23.8Improved
use cross-attention decoder instead of 3-layer MLP (ablation)MRSP with single representation · MIT-States closed-worldAUC: 8.2 -> 12.6Improved
add pre-norm in GCN (ablation)MRSP · MIT-States closed-worldAUC: 20.0 -> 23.8Improved
widen GCN first layer from 4096 to 8192 (ablation)MRSP · MIT-States closed-worldAUC: 20.9 -> 23.8Improved
deepen GCN beyond 2 layers (ablation)MRSP · MIT-States closed-worldAUC: 23.8 -> 22.5 (d8192 x 2)Hurt
use 3 MLP layers instead of 2 in cross-attention (ablation)MRSP · MIT-States closed-worldAUC: 23.8 -> 22.5Hurt
use 8 or 32 attention heads instead of 16 (ablation)MRSP · MIT-States closed-worldAUC: 23.8 -> 22.4 (8 heads), 22.0 (32 heads)Hurt
combine primitive scores additively instead of multiplicatively at inference (ablation)MRSP · MIT-States closed-worldAUC: 19.7 -> 23.8Improved
use stronger backbone ViT-L/14 instead of ResNet18 (ablation)MRSP · MIT-States closed-worldAUC: 9.9 -> 23.8Improved
MRSP versus Troika on best unseen accuracyMRSP · MIT-States closed-worldbest unseen accuracy: 53.0 -> 52.7No clear effect

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