AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

Wentao Bao, Lichang Chen, Heng Huang, Yu Kong

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 36 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 language-informed distribution (LID) over LLM descriptions (ablation)PLID baseline · MIT-States (closed-world)AUC: 18.56 -> 20.43Improved
add text and visual feature enhancement (ablation)PLID · MIT-States (closed-world)AUC: 20.43 -> 21.09Improved
add primitive decomposition for fused decision (ablation)PLID · MIT-States (closed-world)AUC: 21.67 -> 22.12Improved
use larger LLMs (GPT-3.5, Mistral-7B) instead of OPT-1.3B for descriptions (ablation)PLID · MIT-States (closed-world)AUC: 22.12 -> 20.61 (GPT-3.5), 20.78 (Mistral-7B)Hurt
use 3 cross-attention layers instead of 1 in TFE and VFE (ablation)PLID · MIT-States (closed-world)AUC: 22.12 -> 20.65Hurt
use stochastic instead of deterministic logit fusion (ablation)PLID · MIT-States (closed-world)AUC: 21.90 -> 22.12Improved
decompose both visual and text features rather than text only (ablation)PLID · MIT-States (closed-world)AUC: 21.31 -> 21.69Improved
apply LID on states and objects in addition to compositions (ablation)PLID · MIT-States (closed-world)AUC: 21.90 -> 22.12Improved
apply LID on states and objects only (no composition level) (ablation)PLID · MIT-States (closed-world)AUC: 21.67 -> 21.62No clear effect
share covariance across attributes of the same object (ablation)PLID · MIT-States (closed-world)AUC: 22.12 -> 21.69; memory 22.2 -> 17.6 GBHurt
PLID with LLM-informed distributions vs ProDA learned prompt distributionsCLIP-based CZSL · MIT-States (closed-world)AUC: 16.1 -> 20.43Improved

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