AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

DeeCap: Dynamic Early Exiting for Efficient Image Captioning

Zhengcong Fei, Xu Yan, Shuhui Wang, Qi Tian

CVPR 2022 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 40 citations (OpenAlex)

Check 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 imitated deep representations to the early-exit model (ablation)DeeCap · MS COCO offline test, 4× speed-upCIDEr: 127.8 -> 129.0Improved
add imitated deep representations to the early-exit model (ablation)DeeCap · MS COCO offline test, 4× speed-upFCS: 79.55 -> 82.40Improved
add imitated deep representations to the early-exit model (ablation)DeeCap · MS COCO offline test, 2× speed-upCIDEr: 128.3 -> 129.5Improved
use concatenation fusion instead of average fusion (ablation)DeeCap · MS COCO offline testBLEU-4: 38.3 -> 38.7Improved
replace concatenation fusion with attention-pooling (ablation)DeeCap · MS COCO offline testBLEU-4: 38.7 -> 38.6Hurt
replace concatenation fusion with SeqNN (ablation)DeeCap · MS COCO offline testBLEU-4: 38.7 -> 38.5Hurt
use dynamic early exiting with multilevel feature fusion instead of vanilla early exitingimage captioning on MS COCO Karpathy test · MS COCO Karpathy testCIDEr: 126.3 -> 129.0Improved
use dynamic early exiting with multilevel feature fusion instead of vanilla early exitingimage captioning on MS COCO Karpathy test · MS COCO Karpathy testSpeedUp: 4.54× -> 4.35×Mixed

Later papers that compared with this method

1 later accepted paper reports DeeCap as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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