Research map / Label-efficient and robust learning / Recognition and long-tail
Causal Transportability for Visual Recognition
Chengzhi Mao, Kevin Xia, James Wang, Hao Wang, Junfeng Yang, Elias Bareinboim, Carl Vondrick
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 |
|---|---|---|---|
| estimate the causal effect using neural representations and marginalize over sampled images | visual classifiers · CMNIST OOD | accuracy: 29.6% -> 51.4% | Improved |
| use a single forward pass at inference instead of marginalizing over sampled representations and images (ablation) | Causal-Transportability Model · CMNIST OOD | accuracy: 38.8% -> 51.4% | Hurt |
| estimate the causal effect using neural representations and marginalize over sampled images | WaterBird classifier with ResNet50 representation · WaterBird OOD | accuracy: 52.0% -> 77.9% | Improved |
| use a single forward pass at inference instead of marginalizing over sampled representations and images (ablation) | Causal-Transportability Model · WaterBird OOD | accuracy: 71.6% -> 77.9% | Hurt |
| estimate the causal effect using neural representations and marginalize over sampled images | ImageNet-9 classifier with Moco-v2 representation · ImageNet-9 Adversarial Backgrounds OOD | accuracy: 14.59% -> 18.02% | Improved |
| use a single forward pass at inference instead of marginalizing over sampled representations and images (ablation) | Causal-Transportability Model with Moco-v2 representation · ImageNet-9 Adversarial Backgrounds OOD | accuracy: 17.04% -> 18.02% | Hurt |
| estimate the causal effect using neural representations and marginalize over sampled images | ImageNet-9 classifier with SWAV representation · ImageNet-9 Adversarial Backgrounds OOD | accuracy: 20.00% -> 20.42% | Improved |
| use a single forward pass at inference instead of marginalizing over sampled representations and images (ablation) | Causal-Transportability Model with SWAV representation · ImageNet-9 Adversarial Backgrounds OOD | accuracy: 20.25% -> 20.42% | Hurt |
| estimate the causal effect using neural representations and marginalize over sampled images | ImageNet-9 classifier with SimCLR representation · ImageNet-9 Adversarial Backgrounds OOD | accuracy: 27.73% -> 29.41% | Improved |
| use a single forward pass at inference instead of marginalizing over sampled representations and images (ablation) | Causal-Transportability Model with SimCLR representation · ImageNet-9 Adversarial Backgrounds OOD | accuracy: 28.44% -> 29.41% | Hurt |
| estimate the causal effect using neural representations and marginalize over sampled images | ImageNet classifiers with contrastive representations · ImageNet-Rendition and ImageNet-Sketch | accuracy | Mixed |
| increase the number of sampled images X' at inference | Causal-Transportability Model · CMNIST, WaterBird, ImageNet-Rendition, and ImageNet-Sketch | accuracy | Improved |
Closest papers by meaning
- In Pursuit of Causal Label Correlations for Multi-label Image Recognition (NeurIPS 2024 · similarity 0.88)
- Causal Representation Learning Made Identifiable by Grouping of Observational Variables (ICML 2024 · similarity 0.88)
- Transportable Representations for Domain Generalization (AAAI 2024 · similarity 0.87)
- Visual Representation Learning through Causal Intervention for Controllable Image Editing (CVPR 2025 · similarity 0.87)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.87)
- Causal Inference over Visual-Semantic-Aligned Graph for Image Classification (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.
