Papers › Progressively Normalized Self-Attention Network for Video Polyp Segmentation

Progressively Normalized Self-Attention Network for Video Polyp Segmentation

18 May 2021arXiv:2105.08468archive 2025-07-28

Ge-Peng Ji, Yu-Cheng Chou, Deng-Ping Fan, Geng Chen, Huazhu Fu, Debesh Jha, Ling Shao

Existing video polyp segmentation (VPS) models typically employ convolutional neural networks (CNNs) to extract features. However, due to their limited receptive fields, CNNs can not fully exploit the global temporal and spatial information in successive video frames, resulting in false-positive segmentation results. In this paper, we propose the novel PNS-Net (Progressively Normalized Self-attention Network), which can efficiently learn representations from polyp videos with real-time speed (~140fps) on a single RTX 2080 GPU and no post-processing. Our PNS-Net is based solely on a basic normalized self-attention block, equipping with recurrence and CNNs entirely. Experiments on challenging VPS datasets demonstrate that the proposed PNS-Net achieves state-of-the-art performance. We also conduct extensive experiments to study the effectiveness of the channel split, soft-attention, and progressive learning strategy. We find that our PNS-Net works well under different settings, making it a promising solution to the VPS task.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

GewelsJI/FSNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Full-Duplex Strategy for Video Object Segmentation (arXiv:2108.03151; that paper's own run record: 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
GewelsJI/PNS-Net mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video Polyp Segmentation: A Deep Learning Perspective (arXiv:2203.14291; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
gewelsji/vps mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video Polyp Segmentation: A Deep Learning Perspective (arXiv:2203.14291; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

SegmentationVideo Polyp Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Polyp Segmentation SUN-SEG-Easy (Unseen) PNSNet Dice 0.676 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) PNSNet S measure 0.767 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) PNSNet Sensitivity 0.574 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) PNSNet mean E-measure 0.744 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) PNSNet mean F-measure 0.664 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) PNSNet weighted F-measure 0.616 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) PNSNet Dice 0.675 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) PNSNet S-Measure 0.767 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) PNSNet Sensitivity 0.579 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) PNSNet mean E-measure 0.755 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) PNSNet mean F-measure 0.656 #10 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) PNSNet weighted F-measure 0.609 #10 of 18 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