AI Paper Atlas

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

Easy2Hard: From Partially to Fully Unmatched Modalities as Negative Samples in Contrastive Learning

Zhicheng Yang, Yichen Liu, Chang Ge, Xiaopeng Jiang

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory

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
use Easy2Hard partial/full negative split with curriculum instead of Symile uniform negativesSymile (TC/MIP) · EH-MIMICAcc@1: 0.477 -> 0.503Improved
use Easy2Hard instead of SymileSymile (TC/MIP) · ChannelAcc@1: 0.567 -> 0.573No clear effect
use Easy2Hard instead of SymileSymile (TC/MIP) · Symile-MIMICAcc@1: 0.434 -> 0.462Improved
use Easy2Hard instead of SymileSymile (TC/MIP) · MM-IMDbAcc@1: 0.404 -> 0.421Improved
use Easy2Hard instead of Symile with 5 modalitiesSymile (TC/MIP) · HoloAssist (5-modal)Acc@1: 0.833 -> 0.882Improved
use Easy2Hard instead of pivot-based ImageBind-like alignmentImageBind-like baseline · HoloAssist (5-modal)Acc@1: 0.439 -> 0.882Improved
use sigmoid curriculum instead of linear schedule (ablation)Easy2Hard · ChannelAcc@1: 0.494 -> 0.573Improved
use sigmoid curriculum instead of linear schedule (ablation)Easy2Hard · EH-MIMICAcc@1: 0.441 -> 0.503Improved
increase sigmoid slope k from 0.5 to 0.7 (tm=15) (ablation)Easy2Hard · EH-MIMICAcc@1: 0.488 -> 0.446Hurt
vary midpoint tm from 11 to 19 (k=0.3) (ablation)Easy2Hard · ChannelAcc@1: 0.562 -> 0.562 (peak 0.576 at tm=15)No clear effect

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