AI Paper Atlas

Research map / Detection and segmentation / CNN features

OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers

Jialun Pei, Tianyang Cheng, Deng-Ping Fan, He Tang, Chuanbo Chen, Luc Van Gool

ECCV 2022 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 91 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LST encoder (ablation)OSFormer · COD10K-TestAP: 33.7 -> 41.0Improved
add location-guided queries instead of learnable embeddings (ablation)OSFormer · COD10K-TestAP: 35.0 -> 41.0Improved
use location-guided queries instead of zero-initialized queries (ablation)OSFormer · COD10K-TestAP: 34.7 -> 41.0Improved
add BC-FFN in place of vanilla FFN (ablation)OSFormer · COD10K-TestAP: 37.2 -> 41.0Improved
add CFF (multi-scale) instead of single T2 (ablation)OSFormer · COD10K-TestAP: 38.0 -> 41.0Improved
add reverse edge attention (ablation)OSFormer · COD10K-TestAP: 39.3 -> 41.0Improved
encoder layers 6 vs 1 (decoder 3) (ablation)LST · COD10K-TestAP: 37.0 -> 41.0Improved
increase decoder layers from 3 to 6 (encoder 6) (ablation)LST · COD10K-TestAP: 41.0 -> 40.6Hurt
add C2 to multi-scale inputs (C3-C5 to C2-C5) (ablation)LST · COD10K-TestAP: 41.0 -> 39.9Hurt
replace T2-T5 with CNN C2-C5 in CFF (ablation)CFF · COD10K-TestAP: 41.0 -> 35.4Hurt
swap ResNet-50 for Swin-T (ablation)OSFormer · COD10K-TestAP: 41.0 -> 47.7Improved
swap ResNet-50 for ResNet-101 (ablation)OSFormer · COD10K-TestAP: 41.0 -> 42.0Improved

Later papers that compared with this method

2 later accepted papers report OSFormer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy