AI Paper Atlas

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

Mutually Causal Semantic Distillation Network for Zero-Shot Learning

Shiming Chen, Shuhuang Chen, Guo-Sen Xie, Xinge You

IJCV 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 1 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
add semantic distillation loss to the AVCA sub-net (ablation)MSDN++ · CUBH: 68.9 -> 69.8Improved
add semantic distillation loss to the AVCA sub-net (ablation)MSDN++ · AWA2H: 70.7 -> 72.3Improved
add semantic distillation loss to the VACA sub-net (ablation)MSDN++ · CUBH: 61.3 -> 62.5Improved
add semantic distillation loss to the VACA sub-net (ablation)MSDN++ · AWA2H: 64.3 -> 67.3Improved
add causal visual learning (AVCA causal loss) (ablation)MSDN++ · CUBH: 69.6 -> 70.6Improved
add causal attribute learning (VACA causal loss) (ablation)MSDN++ · CUBH: 70.4 -> 70.6Improved
add causal learning losses (ablation)MSDN++ · AWA2H: 71.7 -> 72.5Improved
add causal learning losses (ablation)MSDN++ · CUBH: 69.4 -> 70.6Improved
add a single attention sub-net (AVCA) to the baseline (ablation)baseline · AWA2H: 30.5 -> 70.7Improved
add a single attention sub-net (AVCA) to the baseline (ablation)baseline · CUBH: 49.1 -> 68.9Improved
add attribute regression loss to the baseline (ablation)baseline · CUBH: 49.1 -> 50.2Improved
replace random attention with reversed or uniform attention interventions (ablation)MSDN++ · CUBH: 70.6 -> 70.4No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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