AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

TiCRL: Textual Image Classification with Reinforcement Learning-Based Curriculum Learning

Gayoung KIM, Yuncheol Kang

ECCV 2026 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 0 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 RL-based curriculum (TiCRL)CNN · RVL-CDIP CNN from scratchaccuracy: 80.43 -> 83.67Improved
add RL-based curriculum (TiCRL) vs equal-data baselineCNN · RVL-CDIP CNN from scratchaccuracy: 78.69 -> 83.67Improved
replace linear/step/root predefined schedule with RL schedulerTiCRL · RVL-CDIP CNN from scratchaccuracy: 76.96 -> 83.67Improved
replace SPL/ACL with RL schedulerTiCRL · RVL-CDIP CNN from scratchaccuracy: 75.84 -> 83.67Improved
add RL agent instead of EMA threshold heuristic (ablation)TiCRL · RVL-CDIP CNN from scratchaccuracy: 81.49 -> 83.67Improved
restrict action to 1D threshold adjustment instead of 2D action (ablation)TiCRL · RVL-CDIP CNN from scratchaccuracy: 72.30 -> 83.67Improved
add Canny edge feature to difficulty measurer (ablation)TiCRL · RVL-CDIP CNN (ablation seed)accuracy: 81.40 -> 85.05Improved
add HOG feature to difficulty measurer (ablation)TiCRL · RVL-CDIP CNN (ablation seed)accuracy: 81.63 -> 85.05Improved
add GLCM contrast feature to difficulty measurer (ablation)TiCRL · RVL-CDIP CNN (ablation seed)accuracy: 81.07 -> 85.05Improved
add GLCM homogeneity feature to difficulty measurer (ablation)TiCRL · RVL-CDIP CNN (ablation seed)accuracy: 82.35 -> 85.05Improved
add cosine similarity feature to difficulty measurer (ablation)TiCRL · RVL-CDIP CNN (ablation seed)accuracy: 81.23 -> 85.05Improved
apply TiCRL to DiT fine-tuningDiT · RVL-CDIPaccuracy: 91.07 -> 93.02Improved

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