AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Ladder Loss for Coherent Visual-Semantic Embedding

Mo Zhou, Zhenxing Niu, Le Wang, Zhanning Gao, Qilin Zhang, Gang Hua

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 37 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
Replace VSE++ ranking loss with the ladder lossResNet-152 visual-semantic embedding · MS-COCO (1000 Test Samples), image→sentenceCS@100: 0.238 -> 0.265Improved
Replace VSE++ ranking loss with the ladder lossResNet-152 visual-semantic embedding · MS-COCO (1000 Test Samples), image→sentenceR@1: 63.2 -> 66.7Improved
Replace VSE++ ranking loss with the ladder lossResNet-152 visual-semantic embedding · Flickr30K, image→sentenceCS@100: 0.126 -> 0.133Improved
Add a nonzero β₂ ladder term (β₂=0.25 rather than 0) (ablation)CVSE++ (Res152) · MS-COCO, image→sentenceCS@100: 0.238 -> 0.265Improved
Increase β₂ from 0.25 to 1.0 (ablation)CVSE++ (Res152) · MS-COCO, image→sentenceR@1: 66.7 -> 64.0Hurt
Increase ladder count from L=1 to L=2 (ablation)CVSE++ (Res152) · MS-COCO, image→sentenceCS@100: 0.238 -> 0.265Improved
Increase ladder count from L=2 to L=3 (ablation)CVSE++ (Res152) · MS-COCO, image→sentenceCS@200: 0.252 -> 0.274Improved
Increase ladder count from L=2 to L=3 (ablation)CVSE++ (Res152) · MS-COCO, image→sentenceCS@100: 0.265 -> 0.267Improved
Increase ladder count beyond the chosen setting (the paper notes L=5) (ablation)CVSE++ · MS-COCOR@KHurt

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