</> Code with Papers by Syntology

Papers › Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised...

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

10 Sep 2020archive 2025-07-28

Yun Liu, Yu-Huan Wu, Pei-Song Wen, Yu-Jun Shi, Yu Qiu, Ming-Ming Cheng

Weakly supervised semantic instance segmentation with only image-level supervision, instead of relying on expensive pixel wise masks or bounding box annotations, is an important problem to alleviate the data-hungry nature of deep learning. In this paper, we tackle this challenging problem by aggregating the image-level information of all training images into a large knowledge graph and exploiting semantic relationships from this graph. Specifically, our effort starts with some generic segment-based object proposals (SOP) without category priors. We propose a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels. For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph. The category of background is also included in this graph to remove the massive noisy object proposals. An optimal multi-way cut of this graph can thus assign a reliable category label to each proposal. The denoised SOP with assigned category labels can be viewed as pseudo instance segmentation of training images, which are used to train fully supervised models. The proposed approach achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation.

PaperPDFCode

Code

yun-liu/LIID mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Image-level Supervised Instance SegmentationInstance SegmentationMultiple Instance LearningSegmentationSemantic SegmentationWeakly-Supervised Semantic SegmentationWeakly-supervised instance segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-level Supervised Instance Segmentation COCO test-dev LIID AP 16.0 #4 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev LIID AP@50 27.1 #4 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev LIID AP@75 16.5 #4 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val LIID mAP@0.5 48.4 #7 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val LIID mAP@0.75 24.9 #7 of 13 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 test LIID Mean IoU 67.5 #57 of 60 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val LIID (Res2Net-101) Mean IoU 69.4 #49 of 73 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val LIID (ResNet-101, +24K SI) Mean IoU 67.8 #60 of 73 Archive leaderboard report
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val LIID (ResNet-101) Mean IoU 66.5 #66 of 73 Archive leaderboard report
Weakly-supervised instance segmentation PASCAL VOC 2012 val LIID Average Best Overlap 50.8 #2 of 6 Archive leaderboard report
Weakly-supervised instance segmentation PASCAL VOC 2012 val LIID mAP@0.25 - #2 of 6 Archive leaderboard report
Weakly-supervised instance segmentation PASCAL VOC 2012 val LIID mAP@0.5 48.4 #2 of 6 Archive leaderboard report
Weakly-supervised instance segmentation PASCAL VOC 2012 val LIID mAP@0.75 24.9 #2 of 6 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.

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