AI Paper Atlas

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

Cross-modal Active Complementary Learning with Self-refining Correspondence

Yang Qin, Yuan Sun, Dezhong Peng, Joey Tianyi Zhou, Xi Peng, Peng Hu

NeurIPS 2023 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 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
Apply CRCL (ACL with SCC) to SGRAFSGRAF · Flickr30K, 80% noiserSum: 426.8 -> 443.7Improved
Apply CRCL (ACL with SCC) to SGRAFSGRAF · MS-COCO 1K, 80% noiserSum: 480.1 -> 501.8Improved
Apply CRCL (ACL with SCC)SGRAF · CC152KrSum: 370.2 -> 373.7Improved
Apply CRCL under 20% noiseSGRAF · MS-COCO 5KrSum: 289.4 -> 433.3Improved
Use ACL instead of active loss L_d alone while retaining SCC (ablation)VSE∞ · Flickr30K, 60% noiserSum: 471.2 -> 476.1Improved
Use ACL instead of complementary loss L_r while retaining SCC (ablation)VSE∞ · Flickr30K, 60% noiserSum: 471.6 -> 476.1Improved
Set q=1 in complementary loss and remove SCC (ablation)VSE∞ · Flickr30K, 60% noiserSum: 476.1 -> 267.2Hurt
Set q=0 in complementary loss and remove SCC (ablation)VSE∞ · Flickr30K, 60% noiserSum: 476.1 -> 451.7Hurt
Use active loss L_d alone and remove SCC (ablation)VSE∞ · Flickr30K, 60% noiserSum: 476.1 -> 451.3Hurt
Increase momentum coefficient β from 0 or 1 to an intermediate value (ablation)SCC · Flickr30K, 60% noiseretrieval performanceImproved
Choose τ outside the recommended 0.03–0.07 range (ablation)CRCL-VSE∞ · Flickr30K, 60% noiseretrieval performanceHurt
Filter confident noisy pairs using ε=0.1 (ablation)SCC and ACL · Flickr30K, 60% noiseretrieval performanceImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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