Research map / Detection and segmentation / Weakly supervised detection and segmentation
DANet: Divergent Activation for Weakly Supervised Object Localization
Haolan Xue, Chang Liu, Fang Wan, Jianbin Jiao, Xiangyang Ji, Qixiang Ye
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 hierarchical divergent activation (HDA) to CAM (ablation) | VGG16 CAM · CUB-200-2011 | top-1 loc. err. (%): 55.85 -> 50.71 | Improved |
| add HDA to CAM (ablation) | VGG16 CAM · CUB-200-2011 | top-1 cls. err. (%): 23.42 -> 24.13 | Hurt |
| add discrepant divergent activation (DDA) on top of HDA (ablation) | VGG16 HDA · CUB-200-2011 | top-1 loc. err. (%): 50.71 -> 47.48 | Improved |
| add DDA on top of HDA (ablation) | VGG16 HDA · CUB-200-2011 | top-5 loc. err. (%): 43.48 -> 38.04 | Improved |
| add multi-scale losses on a feature pyramid without DA modules (ablation) | VGG16 CAM · CUB-200-2011 | top-1 loc. err. (%): 55.85 -> 58.58 | Hurt |
| add more hierarchy levels of supervision (one, two, three) (ablation) | HDA · CUB-200-2011 | loc. err. (%): 55.85 -> 52.80 -> 50.71 | Improved |
| randomly drop half of the discrepant activation maps in each mini-batch (ablation) | DDA · CUB-200-2011 | localization | Improved |
| set K=8 activation maps and lambda=0.01 (ablation) | DDA · CUB-200-2011 | loc. err. | Improved |
| use DANet instead of ACoL on VGG16 | VGG16 · CUB-200-2011 | top-1 loc. err. (%): 54.08 -> 47.48 | Improved |
| use DANet instead of SPG on VGG16 | VGG16 · CUB-200-2011 | top-1 loc. err. (%): 51.07 -> 47.48 | Improved |
| use DANet instead of ACoL on GoogLeNet | GoogLeNet · ILSVRC validation | top-1 loc. err. (%): 53.28 -> 52.47 | Improved |
| use DANet instead of SPG on GoogLeNet | GoogLeNet · ILSVRC validation | top-1 loc. err. (%): 51.40 -> 52.47 | No clear effect |
Later papers that compared with this method
31 later accepted papers report DANet as a baseline in their results tables; 28 of them report a better number on most of the results they share with it.
- Anomaly Detection of Integrated Circuits Package Substrates Using the Large Vision Model SAIC: Dataset Construction, Methodology, and Application (ICCV 2025 · better on 2 of 2 shared results)
- Progressive Bayesian Inference for Scribble-Supervised Semantic Segmentation (AAAI 2023 · better on 0 of 1 shared result)
- tSF: Transformer-Based Semantic Filter for Few-Shot Learning (ECCV 2022 · better on 2 of 2 shared results)
- Large-Field Contextual Feature Learning for Glass Detection (TPAMI 2022 · better on 1 of 1 shared result)
- Region-Aware Contrastive Learning for Semantic Segmentation (ICCV 2021 · better on 2 of 2 shared results)
- Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing (ICCV 2021 · better on 2 of 2 shared results)
- Region-aware Global Context Modeling for Automatic Nerve Segmentation from Ultrasound Images (AAAI 2021 · better on 1 of 1 shared result)
- Rethinking Semantic Segmentation From a Sequence-to-Sequence Perspective With Transformers (CVPR 2021 · better on 0 of 1 shared result)
23 more not listed.
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
- Bridging the Gap Between Classification and Localization for Weakly Supervised Object Localization (CVPR 2022 · similarity 0.89)
- Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization (CVPR 2021 · similarity 0.88)
- Rethinking Class Activation Mapping for Weakly Supervised Object Localization (ECCV 2020 · similarity 0.88)
- Strengthen Learning Tolerance for Weakly Supervised Object Localization (CVPR 2021 · similarity 0.88)
- Coarse2Fine: Local Consistency Aware Re-prediction for Weakly Supervised Object Localization (AAAI 2023 · similarity 0.87)
- Self-Supervised Object Localization with Joint Graph Partition (AAAI 2022 · similarity 0.87)
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.
