Research map / Label-efficient and robust learning / Domain adaptation and generalization
Seeing Through the Shift: Causality-Inspired Robust Generalized Category Discovery
Wei Feng, Yiwen Jiang, Sijin Zhou, Zhuang Qi, Zhongxing Xu, Zhonghua Wang, Feilong Tang, Zongyuan Ge
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 source causal dependency risk LP (ablation) | CausalGCD · DomainNet Real+Painting (target Painting) | clustering accuracy (All): 42.8 -> 48.0 | Improved |
| add target causal dependency risk LQ (ablation) | CausalGCD · DomainNet Real+Painting (target Painting) | clustering accuracy (All): 42.4 -> 48.0 | Improved |
| add KL term LKL (ablation) | CausalGCD · DomainNet Real+Painting (target Painting) | clustering accuracy (All): 45.8 -> 48.0 | Improved |
| add exogeneity prototype-alignment loss Le (ablation) | CausalGCD · DomainNet Real+Painting (target Painting) | clustering accuracy (All): 44.6 -> 48.0 | Improved |
| add Causal Geometric Manifold Constraint (ablation) | CausalGCD · DomainNet Real+Painting (target Painting) | clustering accuracy (All): 45.0 -> 48.0 | Improved |
| add Lsep separation loss (ablation) | CausalGCD · DomainNet Real+Painting (target Painting) | clustering accuracy (All): 46.3 -> 48.0 | Improved |
| add Causal Geometric Manifold Constraint (ablation) | CausalGCD · DomainNet Real+Painting (target Painting, New) | clustering accuracy (New): 42.8 -> 46.4 | Improved |
| add LP loss (ablation) | CausalGCD · DomainNet Real+Painting (source Real) | clustering accuracy (All): 63.4 -> 69.9 | Improved |
| use CausalGCD instead of FREE | CausalGCD · DomainNet Real+Painting (target Painting) | clustering accuracy (All): 45.6 -> 48.0 | Improved |
| use CausalGCD instead of FREE | CausalGCD · SSB-C CUB-C (corrupted) | clustering accuracy (All): 55.7 -> 57.8 | Improved |
| vary loss weights lambda1-lambda5 (ablation) | CausalGCD · DomainNet Real+Painting | clustering accuracy | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FREE — FREE: Feature Refinement for Generalized Zero-Shot Learning (ICCV 2021) · better on 9 of 9 shared results
- SPTNet — SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning (ICLR 2024) · 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
- Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective (NeurIPS 2025 · similarity 0.89)
- Towards Understanding Parametric Generalized Category Discovery on Graphs (ICML 2025 · similarity 0.88)
- HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts (ICLR 2025 · similarity 0.88)
- HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery (NeurIPS 2025 · similarity 0.88)
- Transfer and Alignment Network for Generalized Category Discovery (AAAI 2024 · similarity 0.87)
- Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery (AAAI 2025 · 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.
