Layer Transferability Explorer

Transfer Setup

Split layer (freeze 1…k, retrain k+1…10) 5

Target dataset size 2,000

Fine-tune frozen layers (low LR)

Show random-init baseline

Live Readouts

Target accuracy

—%

Trainable params

—%

Relative train time

—×

Co-adaptation loss

—pt

Accuracy vs Split Layer

Current setting Random-init baseline

How it works

A pretrained network is a stack of layers. Early layers learn general features (edges, colors, textures) that transfer well to almost any task; late layers learn features specific to the source task. Transfer learning freezes the general layers 1…k, replaces layers k+1…10 with fresh random weights, and trains only the new part on the target dataset.

specificity(i) = (i / 10)^1.5           // grows with depth
scratchAcc(D)  = 45 + 40 · frac(D)      // baseline, frac = log-scaled dataset size in [0,1]
transferBonus(k) = 18 · (1 − frac) · mean(1 − specificity(1..k))
coAdaptDip(k)  = (fineTune ? 2 : 14) · sin(π·k/10)
fineTuneBonus  = fineTune ? 6 · frac : 0
accuracy = clamp(scratchAcc + transferBonus − coAdaptDip + fineTuneBonus, 0, 99)

Split layer — how deep the frozen, transferred backbone goes. Freezing more of the general early layers helps most when the target dataset is small; freezing too far into the network drags in source-specific features that don't transfer as well.
Co-adaptation dip — splitting mid-network without fine-tuning breaks the fragile interdependence between adjacent layers (Yosinski et al., 2014), producing a real accuracy dip that peaks around the middle split. Enabling fine-tuning lets the frozen layers adapt slightly and mostly closes the gap.
Dataset size — with very little target data, transferring features beats training from scratch by a wide margin; with a lot of data, the gap narrows since a from-scratch network can learn its own good features.
Random-init baseline — the accuracy curve you'd get training all 10 layers from scratch on the target data alone, for comparison.

This is a simplified, formula-driven model of a real and widely measured phenomenon in deep learning, not a live neural-network training run.

Frozen · general features Frozen · source-specific Trainable · target head

⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.