Papers › Learning Instance Activation Maps for Weakly Supervised Instance Segmentation

Learning Instance Activation Maps for Weakly Supervised Instance Segmentation

1 Jun 2019CVPR 2019 6archive 2025-07-28

Yi Zhu, Yanzhao Zhou, Huijuan Xu, Qixiang Ye, David Doermann, Jianbin Jiao

Discriminative region responses residing inside an object instance can be extracted from networks trained with image-level label supervision. However, learning the full extent of pixel-level instance response in a weakly supervised manner remains unexplored. In this work, we tackle this challenging problem by using a novel instance extent filling approach. We first design a process to selectively collect pseudo supervision from noisy segment proposals obtained with previously published techniques. The pseudo supervision is used to learn a differentiable filling module that predicts a class-agnostic activation map for each instance given the image and an incomplete region response. We refer to the above maps as Instance Activation Maps (IAMs), which provide a fine-grained instance-level representation and allow instance masks to be extracted by lightweight CRF. Extensive experiments on the PASCAL VOC12 dataset show that our approach beats the state-of-the-art weakly supervised instance segmentation methods by a significant margin and increases the inference speed by an order of magnitude. Our method also generalizes well across domains and to unseen object categories. Without fine-tuning for the specific tasks, our model trained on VOC12 dataset (20 classes) obtains top performance for weakly supervised object localization on the CUB dataset (200 classes) and achieves competitive results on three widely used salient object detection benchmarks.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image-level Supervised Instance SegmentationInstance SegmentationObjectObject DetectionObject LocalizationRGB Salient Object DetectionSalient Object DetectionSemantic SegmentationWeakly-Supervised Object LocalizationWeakly-supervised instance segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val IAM mAP@0.25 45.9 #12 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val IAM mAP@0.5 28.3 #12 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val IAM mAP@0.75 11.9 #12 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CRFSPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections