Papers › Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation

Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation

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

Yunhang Shen, Rongrong Ji, Yan Wang, Yongjian Wu, Liujuan Cao

Weakly supervised learning has attracted growing research attention due to the significant saving in annotation cost for tasks that require intra-image annotations, such as object detection and semantic segmentation. To this end, existing weakly supervised object detection and semantic segmentation approaches follow an iterative label mining and model training pipeline. However, such a self-enforcement pipeline makes both tasks easy to be trapped in local minimums. In this paper, we join weakly supervised object detection and segmentation tasks with a multi-task learning scheme for the first time, which uses their respective failure patterns to complement each other's learning. Such cross-task enforcement helps both tasks to leap out of their respective local minimums. In particular, we present an efficient and effective framework termed Weakly Supervised Joint Detection and Segmentation (WS-JDS). WS-JDS has two branches for the above two tasks, which share the same backbone network. In the learning stage, it uses the same cyclic training paradigm but with a specific loss function such that the two branches benefit each other. Extensive experiments have been conducted on the widely-used Pascal VOC and COCO benchmarks, which demonstrate that our model has achieved competitive performance with the state-of-the-art algorithms.

Paper PDF Code

Code

shenyunhang/WS-JDS officialcaffe2 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 Segmentation Multi-Task Learning Object Object Detection Segmentation Semantic Segmentation Weakly Supervised Object Detection Weakly-supervised Learning object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image-level Supervised Instance Segmentation	COCO 2017 val	WS-JDS	AP	6.1	#6 of 6	Archive leaderboard	report
Image-level Supervised Instance Segmentation	COCO 2017 val	WS-JDS	AP@50	11.7	#6 of 6	Archive leaderboard	report
Image-level Supervised Instance Segmentation	COCO 2017 val	WS-JDS	AP@75	5.5	#6 of 6	Archive leaderboard	report
Weakly Supervised Object Detection	PASCAL VOC 2007	WS-JDS FRCNN	MAP	52.5	#18 of 41	Archive leaderboard	report
Weakly Supervised Object Detection	PASCAL VOC 2012 test	WS-JDS FRCNN	MAP	46.1	#19 of 32	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