AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data

Xihui Liu, Hongsheng Li, Jing Shao, Dapeng Chen, Xiaogang Wang

ECCV 2018 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 143 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 self-retrieval reward (fully labeled) (ablation)CIDEr-reward baseline · COCO Karpathy testCIDEr: 112.7 -> 114.6Improved
add unlabeled images with retrieval-only reward (ablation)SR-FL · COCO Karpathy testCIDEr: 114.6 -> 117.1Improved
add self-retrieval reward (fully labeled) (ablation)CIDEr-reward baseline · COCO Karpathy testBLEU-4: 35.0 -> 34.9No clear effect
add self-retrieval reward and unlabeled data (ablation)CIDEr-reward baseline · Flickr30kCIDEr: 57.1 -> 65.0Improved
add self-retrieval reward (fully labeled) (ablation)CIDEr-reward baseline · Flickr30kCIDEr: 57.1 -> 61.7Improved
use VSE++ instead of VSE0 retrieval loss (ablation)SR-PL · COCO Karpathy test (ablation)CIDEr: 116.9 -> 117.1Improved
use VSE++ instead of softmax retrieval loss (ablation)SR-PL · COCO Karpathy test (ablation)CIDEr: 114.5 -> 117.1Improved
use self-retrieval weight 1 instead of 0 (ablation)SR-PL · COCO Karpathy test (ablation)CIDEr: 112.7 -> 117.1Improved
raise self-retrieval weight from 1 to 4 (ablation)SR-PL · COCO Karpathy test (ablation)CIDEr: 117.1 -> 113.7Hurt
use 1:1 labeled to unlabeled ratio instead of 1:2 (ablation)SR-PL · COCO Karpathy test (ablation)CIDEr: 115.4 -> 117.1Improved
use 1:1 labeled to unlabeled ratio instead of 2:1 (ablation)SR-PL · COCO Karpathy test (ablation)CIDEr: 115.0 -> 117.1Improved
add moderately hard negative mining (range 100-1000) (ablation)SR-PL · COCO Karpathy test (ablation)CIDEr: 114.6 -> 117.1Improved

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