AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Discrete-Continuous Action Space Policy Gradient-Based Attention for Image-Text Matching

Shiyang Yan, Li Yu, Yuan Xie

CVPR 2021 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 35 citations (OpenAlex)

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 discrete-continuous PG-based attentionFlickr30k matching baseline · Flickr30kCaption retrieval R@1: 70.9 -> 81.0Improved
add Instance Loss to Triplet Loss (ablation)Flickr30k matching model · Flickr30kCaption retrieval R@1: 68.2 -> 69.3Improved
add Text Decoding Loss to Triplet + Instance (ablation)Flickr30k matching model · Flickr30kCaption retrieval R@1: 69.3 -> 70.9Improved
use discrete-continuous PG instead of discrete-only PG (ablation)Flickr30k matching model · Flickr30kCaption retrieval R@1: 78.0 -> 81.0Improved
use discrete-continuous PG instead of single-Gaussian continuous PG (ablation)Flickr30k matching model · Flickr30kCaption retrieval R@1: 76.8 -> 81.0Improved
use combined R@1 and AP reward instead of R@1-only reward (ablation)Flickr30k discrete-continuous PG · Flickr30kCaption retrieval R@1: 79.3 -> 81.0Improved
use combined R@1 and AP reward instead of AP-only reward (ablation)Flickr30k discrete-continuous PG · Flickr30kCaption retrieval R@1: 80.4 -> 81.0Improved
set λ to 20 rather than 10 (ablation)Flickr30k discrete-continuous PG · Flickr30kCaption retrieval R@1: 80.2 -> 81.0Improved
set λ to 20 rather than 30 (ablation)Flickr30k discrete-continuous PG · Flickr30kCaption retrieval R@1: 79.2 -> 81.0Improved
add a PG baseline (ablation)Flickr30k discrete-continuous PG · Flickr30kCaption retrieval R@1: 81.0 -> 80.3Hurt
add a multi-head mechanism (ablation)Flickr30k discrete-continuous PG · Flickr30kCaption retrieval R@1: 81.0 -> 81.4Improved
use pre-trained GloVe word embeddings (ablation)Flickr30k discrete-continuous PG · Flickr30kCaption retrieval R@1: 81.0 -> 82.8Improved

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