Research map / Detection and segmentation / Open-set and few-shot detection
Deep Robust Subjective Visual Property Prediction in Crowdsourcing
Qianqian Xu, Zhiyong Yang, Yangbangyan Jiang, Xiaochun Cao, Qingming Huang, Yuan Yao
Check 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 the outlier indicator γ to LS-Deep (ablation) | LS-Deep on FG-Net Face Age · FG-Net Face Age | ACC: .7313 -> .7967 | Improved |
| add the outlier indicator γ to Logit-Deep (ablation) | Logit-Deep on FG-Net Face Age · FG-Net Face Age | ACC: .7439 -> .7917 | Improved |
| add the outlier indicator γ to LS-Deep (ablation) | LS-Deep on LFW-10 · LFW-10 (10 attributes, average) | ACC: .6100 -> .6826 | Improved |
| add the outlier indicator γ to Logit-Deep (ablation) | Logit-Deep on LFW-10 · LFW-10 (10 attributes, average) | ACC: .6000 -> .6694 | Improved |
| add the outlier indicator γ to LS-Deep (ablation) | LS-Deep on Shoes · Shoes (7 attributes, average) | ACC: .7538 -> .8222 | Improved |
| add the outlier indicator γ to Logit-Deep (ablation) | Logit-Deep on Shoes · Shoes (7 attributes, average) | ACC: .7575 -> .8217 | Improved |
| use a deep ResNet-50 Siamese ranker instead of non-deep feature-based methods | SVP prediction · FG-Net Face Age, LFW-10, and Shoes | ACC | Improved |
| jointly model outliers and ranking rather than relying on majority-vote preprocessing | SVP prediction · FG-Net Face Age | ACC: .5940 -> .7967 | Improved |
Closest papers by meaning
- Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels (TPAMI 2016 · similarity 0.93)
- Not All Samples are Trustworthy: Towards Deep Robust SVP Prediction (TPAMI 2020 · similarity 0.93)
- Evaluating Visual Properties via Robust HodgeRank (IJCV 2021 · similarity 0.89)
- Deep Partial Rank Aggregation for Personalized Attributes (AAAI 2021 · similarity 0.86)
- Doomed to Re-Annotate, Forever: The ImageNet Story (NeurIPS 2026 · similarity 0.84)
- Unbiased Multi-Label Learning from Crowdsourced Annotations (ICML 2024 · similarity 0.83)
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.
