Skip to content
Conference

SAM-Anchored DINOv3 Soft Calibration for Weakly Supervised Semantic Segmentation

Aug 2026 · International Conference on Multimedia Analysis and Pattern Recognition · pp. 268-273 · 0 citations · 17 references

Abstract

Weakly supervised semantic segmentation (WSSS) aims to train dense prediction models from inexpensive supervision such as image-level labels. Recent foundation models provide complementary capabilities: promptable segmentation models can produce high-coverage object masks, while self-supervised vision transformers provide discriminative dense representations. However, directly modifying or filtering pseudo-labels can reduce supervision coverage and degrade downstream student training. This paper proposes DINO-SAM SoftCal, a SAM-anchored DI-NOv3 reliability calibration framework for WSSS. The proposed method preserves pseudo-labels generated by a frozen SAM 3.1 model and uses frozen DINOv3 features to construct class-aware prototypes. Instead of changing semantic targets, DINOv3 prototype agreement is used as a soft loss calibration signal for training a DeepLabV3+ student. On PASCAL VOC 2012, the proposed method improves on average over both SAM-only training and a same-checkpoint SAM continuation control. We also reproduce ToCo as an external WSSS reference baseline. On an exploratory MS COCO 2014 subset, the same calibration strategy also improves over the corresponding SAM continuation control. These results suggest that, in our setting, using DINOv3 as a conservative reliability calibrator is an effective way to integrate dense foundation-model features without sacrificing pseudo-label coverage.

View source

Similar papers

2026

Reliability-Calibrated Posterior Supervision for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS) with image-level labels is largely limited by the reliability of dense seed supervision. Existing CAM- and CLIP-based methods provide complementary localization cues, but their predictions are biased in different ways: classification-oriented cues are usually precise but i...

Xiao-Ya Sun, Xin Xu · 0 citations
Aug 2026

MSPD-net: structural–appearance prototype decoupling for weakly supervised semantic segmentation

A complementary prototype representation framework is proposed, employing three modules to collaboratively improve pseudo-label quality and improves the discriminative ability of confused categories by generating semantically similar sub-category negative samples.

Wei Cao, Yong Jiang, Ruiying Wang · 0 citations
Sep 2026

CRF Loss is How Networks Should Learn Boundaries in Weakly Supervised Segmentation

Inspired by CRF potentials, a framework that disentangles soft pseudo-labels as unary supervision and binary edge maps as pairwise supervision is proposed that sets a new state-of-the-art of 56.5% mIoU on MS COCO among training-based methods.

Joshua Li, Yuri Boykov · 0 citations
Conference Open access Sep 2026

RACL: reliability-aware contrastive learning for weakly supervised change detection

An end-to-end framework for weakly supervised change detection is proposed that effectively improves weakly supervised change detection performance and introduces a Reliability-Aware Contrastive Learning strategy to enhance the separability of change representations.

Die-Die Liu, Si-Bao Chen · 0 citations
Preprint Sep 2026

Progressive Pseudo-Label Optimization for Point-Supervised Change Detection

This work proposes a two-stage framework that introduces SAM2 priors into PS-CD and progressively adapts them to the target task, and establishes a closed-loop optimization process that alternates between pseudo-label refinement and model re-optimization.

Hailong Ning, Hao Wang, Yiming Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.