Research map / Vision-language and multimodal / Cross-modal learning
LightAVSeg: Lightweight Audio-Visual Segmentation
Qing Zhong, Guodong Ding, Lingqiao Liu, Zaiwen Feng, Lin Yuanbo Wu, Angela Yao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Audio-Guided Visual Enhancement (AGVE) (ablation) | static-concatenation baseline · AVSBench MS3 | M_J: 44.4 -> 46.8 | Improved |
| add Cross-Modal Fusion Decoder (CMFD) to AGVE (ablation) | AGVE · AVSBench MS3 | M_J: 46.8 -> 48.3 | Improved |
| add Hierarchical Audio Refinement (HAR) to AGVE (ablation) | AGVE · AVSBench MS3 | M_J: 46.8 -> 49.3 | Improved |
| add CMFD and L_msa to full encoder (ablation) | AGVE+HAR · AVSBench MS3 | M_J: 49.3 -> 50.4 | Improved |
| add L_msa auxiliary loss (ablation) | L_seg · AVSBench MS3 | M_J: 49.3 -> 50.4 (+1.1 mIoU) | Improved |
| add L_msa auxiliary loss (ablation) | L_seg · AVSBench MS3 | M_F: 60.8 -> 62.6 (+1.8) | Improved |
| add L_AVM auxiliary loss (ablation) | L_seg · AVSBench MS3 | M_J: 49.3 -> 49.2 | No clear effect |
| add L_mix auxiliary loss (ablation) | L_seg · AVSBench MS3 | M_J: 49.3 -> 48.8 | Hurt |
| use SeaFormer-Tiny instead of SeaFormer-Large visual backbone | LightAVSeg · AVSBench MS3 | M_J: 50.4 -> 30.6 | Hurt |
| use SeaFormer-Base instead of SeaFormer-Large visual backbone | LightAVSeg · AVSBench MS3 | M_J: 50.4 -> 44.2 | Hurt |
| use ResNet-50 instead of SeaFormer-Large visual backbone | LightAVSeg · AVSBench MS3 | M_J: 50.4 -> 52.9; latency 163.4 -> 675.0 ms | Mixed |
| use YamNet instead of MobileNetV2 audio backbone | LightAVSeg · AVSBench MS3 | M_J: 50.4 -> 47.8 | Hurt |
Closest papers by meaning
- AVSegFormer: Audio-Visual Segmentation with Transformer (AAAI 2024 · similarity 0.89)
- Audio-Visual Segmentation via Unlabeled Frame Exploitation (CVPR 2024 · similarity 0.88)
- Audio-Visual Instance Segmentation (CVPR 2025 · similarity 0.88)
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer (AAAI 2024 · similarity 0.87)
- Improving Audio-Visual Segmentation with Bidirectional Generation (AAAI 2024 · similarity 0.87)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.87)
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.
