Learning What to Trust in Multimodal Learning under Noisy Supervision
arXiv:2610.11057v1 Announce Type: new Abstract: Multimodal classification processes and relates information from multiple modalities to achieve more accurate predictions. However, existing methods typically rely on high-quality ground-truth labels, which are difficult to obtain in real-world scenar…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-09 04:00 · arXiv cs.CV
Learning What to Trust in Multimodal Learning under Noisy Supervision