Research

Field-level analysis, literature synthesis, benchmark interpretation, and reliability framing that make the domain easier to reason about.

2 research pieces

Project Notes

Project-linked notes that keep decisions, tradeoffs, and changes in judgment close to the work itself.

2 project notes

Methods

Reusable engineering patterns that make experiments steadier, cleaner, and easier to trust.

4 methods

Technical Notes

Focused concept notes for mechanisms, tradeoffs, and implementation details worth keeping close at hand.

8 technical notes
Technical Note

U-Net Model Architecture

A step-by-step explanation of the U-Net architecture, the problem pressures that shaped it, and why it remains a serious baseline for many dense prediction tasks.

U-Net Dense Prediction Segmentation Architecture Baselines
Technical Note In progress

Squeeze-and-Excitation

How squeeze-and-excitation uses global context to recalibrate channels, why the block stayed cheap enough to spread, and what later attention papers changed.

Attention CNNs Architecture Efficiency

How initialization controls signal and gradient scale, why Xavier and Kaiming rules exist, and what later theory adds about criticality and Jacobian conditioning.

Optimization Initialization Signal Propagation

How encoder-decoder models separate representation learning from output construction, why compression and reconstruction stay in tension, and how the pattern evolved from autoencoders and U-Net to DETR, MAE, diffusion, and SAM.

Encoder-Decoder Dense Prediction Representation Learning Transformers

Why stacked linear layers collapse into one linear transformation, how ReLU prevents that collapse, and why piecewise-linear gating gives deep networks expressive power.

Activations ReLU Neural Networks

How dense-prediction metrics change the object being compared, and why region, boundary, topology, instance, perceptual, and uncertainty errors need different evaluation lenses.

Dense Prediction Metrics Evaluation