Research map / Label-efficient and robust learning / Domain adaptation and generalization
CycleEmotionGAN: Emotional Semantic Consistency Preserved CycleGAN for Adapting Image Emotions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| add emotional semantic consistency loss (Mikels distance) to CycleGAN (ablation) | CycleEmotionGAN · ArtPhoto to FI | average accuracy (%): 22.68 -> 25.20 | Helped |
| add emotional semantic consistency loss (SKL) to CycleGAN (ablation) | CycleEmotionGAN · ArtPhoto to FI | average accuracy (%): 22.68 -> 24.67 | Helped |
| add emotional semantic consistency loss (SKL) to CycleGAN (ablation) | CycleEmotionGAN · FI to ArtPhoto | average accuracy (%): 32.05 -> 37.18 | Helped |
| add emotional semantic consistency loss (Mikels distance) to CycleGAN (ablation) | CycleEmotionGAN · FI to ArtPhoto | average accuracy (%): 32.05 -> 37.18 | Helped |
| use Mikels wheel distance instead of symmetrized KL for ESC loss (ablation) | CycleEmotionGAN · ArtPhoto to FI | average accuracy (%): 24.67 -> 25.20 | Helped |
| use Mikels wheel distance instead of symmetrized KL for ESC loss (ablation) | CycleEmotionGAN · FI to ArtPhoto | average accuracy (%): 37.18 -> 37.18 | No clear effect |
| vary ESC loss weight lambda (ablation) | CycleEmotionGAN · ArtPhoto to FI and FI to ArtPhoto | accuracy | Mixed |
Closest papers by meaning
- Bridge Then Begin Anew: Generating Target-Relevant Intermediate Model for Source-Free Visual Emotion Adaptation (AAAI 2025 · similarity 0.87)
- Multi-Source Domain Adaptation for Visual Sentiment Classification (AAAI 2020 · similarity 0.87)
- MDAN: Multi-Level Dependent Attention Network for Visual Emotion Analysis (CVPR 2022 · similarity 0.85)
- Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition (CVPR 2025 · similarity 0.84)
- Multiple Feature Refining Network for Visual Emotion Distribution Learning (AAAI 2025 · similarity 0.84)
- EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025 · similarity 0.84)
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.