AI Paper Atlas

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

Audio-visual Generalized Zero-shot Learning the Easy Way

Shentong Mo, Pedro Morgado

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 7 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 class embedding optimization (CEO) (ablation)audio-visual GZSL baseline · VGGSound-GZSLharmonic mean: 8.77 -> 10.45Improved
add AVLA supervised contrastive alignment (ablation)audio-visual GZSL baseline · VGGSound-GZSLharmonic mean: 8.77 -> 9.69Improved
add both CEO and AVLA (ablation)audio-visual GZSL baseline · VGGSound-GZSLharmonic mean: 8.77 -> 11.55Improved
add class separability loss to class embedding optimization (ablation)class embedding optimization · VGGSound-GZSLharmonic mean: 10.46 -> 11.55Improved
replace proximity semantic loss with ranking loss (ablation)class embedding optimization · VGGSound-GZSLharmonic mean: 11.55 -> 13.10Improved
use cross-attention similarity instead of cosine similarity (ablation)AVLA · VGGSound-GZSLharmonic mean: 10.64 -> 11.55Improved
use linear or MLP similarity instead of cross-attention (ablation)AVLA · VGGSound-GZSLunseen accuracy: 8.68 -> 8.52 (Linear), 8.46 (MLP)Hurt
increase alpha from 0.5 to 0.9 (ablation)class embedding optimization · VGGSound-GZSLharmonic mean: 13.10 -> 11.36Hurt
decrease margin m from 1 to 0 or 0.5 (ablation)ranking loss · VGGSound-GZSLharmonic mean: 13.10 -> 12.57 (m=0), 12.65 (m=0.5)Hurt
use L1 or L2 distance instead of cosine distance (ablation)class embedding optimization · VGGSound-GZSLharmonic mean: 13.10 -> 12.18 (l2), 11.66 (l1)Hurt
add class embedding optimization with ImageBind encoders (ablation)ImageBind features · VGGSound-GZSLharmonic mean: 19.34 -> 26.90Improved
use stronger pretrained unimodal/paired/unified encodersOurs · VGGSound-GZSLharmonic mean: 11.55 -> 26.90 (ImageBind)Improved

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