CONCEPT Cited by 1 source
Non-Maximum Suppression (NMS)¶
Definition¶
Non-Maximum Suppression (NMS) is the classical object- detection post-processing technique that de-duplicates overlapping bounding-box detections by keeping the highest-confidence box in each overlapping cluster and discarding all others whose IoU with the kept box exceeds a threshold. NMS has been the default output stage in essentially every mainstream object detector (R-CNN family, YOLO, SSD, DETR variants) for a decade.
Mechanism¶
The classical greedy recipe:
- Sort all candidate boxes by confidence, highest first.
- Pick the highest-confidence box; add it to the output set.
- Remove (suppress) every remaining box whose IoU with the picked box exceeds the threshold (typically 0.5).
- Repeat from step 2 until the candidate list is empty.
Result: a de-duplicated set of non-overlapping boxes.
Why it matters (and why it's increasingly contested)¶
NMS is the baseline everyone knows. Its virtues: simple, fast, deterministic, O(N log N). Its weakness: it discards information.
When multiple detectors — or multiple passes of the same detector — produce correct-but-imprecise boxes for the same object, NMS keeps exactly one box and throws the rest away. If the highest-confidence box has slightly wrong coordinates but a lower-confidence box had better coordinates, NMS picks the wrong-coordinate one.
This is the motivating failure that Weighted Boxes Fusion was designed to fix. Instacart's flyer-digitization team explicitly frames the comparison:
"Unlike traditional Non-Maximum Suppression (NMS), which may discard valuable information by eliminating lower-confidence boxes, WBF combines all overlapping boxes by computing a confidence-weighted average of their coordinates." (Source: sources/2026-02-09-instacart-from-print-to-digital-making-weekly-flyers-shoppable)
When to still use NMS¶
- Single-detector, high-signal regime. If one detector is well-calibrated and dominates the others, NMS is fine — there's no low-confidence coordinate information worth preserving.
- Latency-critical inference. NMS is faster than WBF.
- When genuinely distinct nearby objects might merge. WBF's averaging can incorrectly fuse two real adjacent objects; NMS is less aggressive about blending.
Seen in¶
- sources/2026-02-09-instacart-from-print-to-digital-making-weekly-flyers-shoppable — named explicitly as the technique Instacart's flyer- digitization pipeline chose not to use in Phase 1, preferring WBF because NMS "may discard valuable information by eliminating lower-confidence boxes."
Related¶
- concepts/weighted-boxes-fusion — the newer alternative that preserves low-confidence coordinate information
- concepts/model-ensembling-for-detection — multi-detector fusion where NMS's information-loss matters most
- systems/instacart-flyer-digitization-pipeline — pipeline that rejected NMS in favour of WBF
- companies/instacart