Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• HamVision uses the damped harmonic oscillator as a structured inductive bias for medical image segmentation and classification tasks.method 95%
• The oscillator's phase-space decomposition yields three functionally distinct representations: position (feature content), momentum (spatial gradients), and energy (parameter-free saliency map).technical 90%
• HamSeg achieves state-of-the-art Dice scores on ISIC 2018 (89.38%), ISIC 2017 (88.40%), TN3K (87.05%), and ACDC (92.40%).result 92%
• HamSeg outperforms most baselines with only 8.57M parameters.result 88%
• HamCls achieves state-of-the-art accuracy on BloodMNIST (98.85%) and PathMNIST (96.65%).result 90%
• The oscillator's momentum consistently encodes an interior>boundary>exterior gradient for segmentation.technical 85%
• The energy map correlates with discriminative regions for classification.technical 85%
• The three representations emerge from the dynamics, not from supervision, and can be exploited by different task-specific heads without any modification to the oscillator itself.method 88%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card