Glance

Read the score before trusting it

Glance estimates early visual attention. Each score answers a narrower question than “does this design work?”

What goes into a heatmap

Let pᵢ be normalized, nonnegative predicted fixation density at pixel i, with Σpᵢ = 1. An area of interest (AOI) is a region you draw. Attention share describes predicted map mass, not a percentage of viewers.

Scores for reviewing a design

Planned core outputs from the specification
OutputFormula or methodHow to read it
AOI share100 × Σ(i ∈ AOI) pᵢPredicted attention mass inside an area. Overlapping areas can double count.
Clarity100 × [1 − H(p)/ln(4096)]
H(p) = −Σpᵢ ln(pᵢ)
Downsample to 64 × 64 and renormalize first; 0 ln 0 = 0. Concentrated maps score higher. This custom 0–100 index is not validated comprehension.
First glanceRank each AOI by the first estimated fixation that enters it.Unvisited areas have no rank. Fallback: seven peaks, Gaussian inhibition of return and center prior. Approximation; width-based suppression is not calibrated visual angle.
FogDim below the specified “25th percentile mass” threshold.Low predicted attention, not proof of being ignored. TODO-verify: whether implementation uses a pixel quantile or cumulative mass threshold.
AgreementUᵢ = stdₘ(pₘᵢ)
scalar = mean pairwise CC
Ensemble maps aligned to the same grid. High agreement can accompany shared errors. Constant maps make CC undefined.
Compare A/BΔshare = share(B) − share(A)
Δclarity = clarity(B) − clarity(A)
Share deltas in percentage points; report heatmap CC separately. Prediction differences are not causal conversion lift.
VideoUNISAL temporal mode; sample at 5 frames/s.Per-frame heatmaps and AOI shares over time. Target behavior; export and timing verification pending.

Metrics for comparing predictions with people

Let S be a predicted saliency map, G a human fixation density and F the set of recorded fixation locations.

MetricFormulaMeaning and limit
AUC∫₀¹ TPR(FPR) dFPRHow well map scores separate fixated locations from negatives; 0.5 is chance under the chosen protocol. Negative sampling and center bias matter.
CCcov(S,G) / [σ(S) σ(G)]Pearson correlation of map values, −1 to 1; larger is more similar. Undefined for constant maps.
NSSmean(i ∈ F) [(Sᵢ − μ(S))/σ(S)]Average standardized map value at human fixations; higher is better. It is not a percentage. Undefined when σ(S) = 0.

Source: saliency metric review. Read the benchmark evaluation protocol before comparing results.

Reference benchmark, not a Glance result

Supplied MIT/Tübingen reference values; exact row/protocol TODO-verify
ReferenceAUCCCNSS
DeepGaze IIE0.88290.82422.5265
Human gold standard0.93410.9828Not supplied

MIT/Tübingen benchmark · DeepGaze IIE paper. These values do not establish performance of SUM, TranSalNet, UNISAL or an exported ONNX model in Glance.

Commercial “92–96% accuracy” figures may normalize a metric against the human ceiling. For example, 83% / 90% ≈ 92%. That ratio does not mean “correct 92% of the time.” Request the raw metric, denominator, dataset and validation procedure for each claim.

Where prediction stops

Check papers and model licenses

Questions before you start

Is Glance 94% accurate?

No such Glance result is established. Reference benchmark values describe a named research model and protocol, not this application.

Does higher clarity mean a better design?

No. Clarity measures concentration in the predicted map. A very concentrated map can overlook useful information.