Research map / Detection and segmentation / Open-set and few-shot detection
ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, Huchuan Lu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add RGPU to baseline (ablation) | ZoomNeXt baseline · COD10K | S-measure: 0.826 -> 0.843 (G=6) | Improved |
| add MHSIU (M=4) to baseline (ablation) | ZoomNeXt baseline · COD10K | S-measure: 0.826 -> 0.856 | Improved |
| add both RGPU and MHSIU (ablation) | ZoomNeXt baseline · COD10K | S-measure: 0.826 -> 0.861; ARG 6.56% | Improved |
| add uncertainty awareness loss (UAL) (ablation) | ZoomNeXt (RGPU + MHSIU) · COD10K | weighted F-measure: 0.734 -> 0.768 | Improved |
| increase RGPU groups from 6 to 8 (ablation) | RGPU · COD10K | S-measure: 0.843 -> 0.839 | Hurt |
| replace RGPU with Res2Net block (ablation) | ZoomNeXt baseline · COD10K | S-measure: 0.843 -> 0.833 | Hurt |
| increase MHSIU heads from 4 to 8 (ablation) | MHSIU · COD10K | weighted F-measure: 0.728 -> 0.726 | No clear effect |
| use mixed scales 0.5x,1.0x,1.5x with MHSIU instead of single 1.0x input (ablation) | ZoomNeXt baseline · COD10K | S-measure: 0.826 -> 0.856 | Improved |
| use MHSIU instead of addition for fusing three scales (ablation) | mixed-scale input · COD10K | weighted F-measure: 0.719 -> 0.728 | Improved |
| replace max-pooling down-sampling with bi-linear interpolation (ablation) | MHSIU · COD10K | S-measure: 0.856 -> 0.852; ARG down 2.32% | Hurt |
| use cosine instead of constant lambda schedule for UAL (ablation) | UAL · COD10K | S-measure: 0.859 -> 0.861 | No clear effect |
| increase number of input frames from T=1 to T=5 (ablation) | ZoomNeXt · MoCA-Mask-TE | S-measure: 0.690 -> 0.734 | Improved |
Later papers that compared with this method
7 later accepted papers report ZoomNeXt as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- Wavefront-Constrained Passive Obscured Object Detection (AAAI 2026 · better on 4 of 4 shared results)
- IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment (ECCV 2026 · better on 4 of 4 shared results)
- Power Battery Detection (IJCV 2026 · better on 2 of 2 shared results)
- Beyond Appearance: Camouflaged Object Detection via Geometric Structure (CVPR 2026 · better on 1 of 1 shared result)
- Towards Real Zero-Shot Camouflaged Object Segmentation Without Camouflaged Annotations (TPAMI 2025 · better on 3 of 3 shared results)
- Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection (CVPR 2025 · better on 1 of 1 shared result)
- Referring Camouflaged Object Detection (TPAMI 2025 · better on 1 of 1 shared result)
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
- Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection (CVPR 2022 · similarity 0.95)
- Camouflaged Object Detection (CVPR 2020 · similarity 0.90)
- VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection (ECCV 2026 · similarity 0.90)
- ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection (ICCV 2025 · similarity 0.90)
- SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection (AAAI 2025 · similarity 0.88)
- Shift the Lens: Environment-Aware Unsupervised Camouflaged Object Detection (CVPR 2025 · similarity 0.88)
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.
