domains / families / data / tao-analyze-gaps-visual-changenet

tao-analyze-gaps-visual-changenet

separate

Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.

When to use

• Analyzing VCN classification failures
• Picking SDA augmentation targets
• Auditing PASS/NO_PASS boundary cases
• Identifying weakest samples per ground-truth label
• Measuring signed distance from decision threshold

When not to use

• Delegated analysis
• Multi-phase image audits
• Component-type clustering

Skill page

Source