SADe: Sparse-Atom Support Decontamination for Few-Shot Segmentation with Weak Support Annotations
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address a problem in few-shot segmentation where support annotations are often weak or imprecise, such as boxes or scribbles, which can confuse models with irrelevant background or similar textures. They propose SADe, a method that cleans these weak support masks by estimating which parts are reliable using a technique called sparse autoencoder atom evidence. SADe works independently of the query image and improves mask quality without changing the segmentation model’s query-side processing. Their approach consistently improves segmentation accuracy across multiple models and annotation types, showing that their reliability cues go beyond simple similarity measures.
Few-shot segmentationSupport masksWeak supervisionSparse autoencoderAtom evidencePrototype contaminationMask refinementQuery predictionPrompt-based learningmIoU (mean Intersection over Union)
Authors
Hang Xing, Guangjun Liu, Yan Xia, Xueming Ding
Abstract
Few-shot segmentation (FSS) commonly assumes clean pixel-level support masks, yet practical support supervision often uses boxes, scribbles, coarse masks, or pseudo-masks. These weak annotations may include texture-similar distractors and background context alongside the target, contaminating class prototypes or visual prompts before query prediction. We introduce SADe, a predictor-agnostic support decontamination layer that estimates the reliability of selected support patches without query information. Central to SADe is sparse autoencoder (SAE) atom evidence: dense similarity may respond to both target and texture-similar context, whereas contrasting atom activations inside and outside the weak-support region provides factor-level reliability cues. A lightweight router combines atom evidence with dense similarity and episode statistics to predict patch reliability and generate a cleaned support mask. Trained once on synthetic weak-support episodes from FSS-1000, the router is frozen for all target evaluations. The resulting mask supports standalone prediction or can be supplied to heterogeneous FSS models through native support interfaces without altering query-side inference. Under a matched weak-support protocol, SADe achieves the highest query mIoU in six of nine standalone prompt-shot combinations. With the same ProMi query head, it is within 0.03 mIoU of SAM3-derived masks under tight boxes and surpasses them by 11.17 and 19.49 points under box-r2 and box-r4, respectively. As a plug-in, SADe improves over raw support in 70 of 72 matched box-family comparisons across four frozen downstream models and two datasets. On point and scribble prompts, its average performance remains close to the corresponding raw-support baseline. Ablations and atom-removal controls show that atom evidence contributes reliability information beyond dense similarity.