Research map / Vision-language and multimodal / Visual question answering
Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
Zhu Wang, Sourav Medya, Sathya N. Ravi
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 knowledge graph triplets (ablation) | VK-OOD · VQAv2 | accuracy: 73.9 -> 74.6 | Improved |
| add OOD detection layer only (ablation) | VK-OOD · VQAv2 | accuracy: 73.9 -> 74.1 | Improved |
| add both KG and OOD layer (ablation) | VK-OOD · VQAv2 | accuracy: 73.9 -> 76.8 | Improved |
| add knowledge graph triplets (ablation) | VK-OOD · OKVQA | accuracy: 45.5 -> 48.3 | Improved |
| add OOD detection layer only (ablation) | VK-OOD · OKVQA | accuracy: 45.5 -> 46.2 | Improved |
| add both KG and OOD layer (ablation) | VK-OOD · OKVQA | accuracy: 45.5 -> 52.4 | Improved |
| add both KG and OOD layer (ablation) | VK-OOD · NLVR2 | accuracy: 80.6 -> 83.9 | Improved |
| increase number of retrieved knowledge triplets | VK-OOD · OKVQA | accuracy: 52.4 | Improved |
| add BERT knowledge encoder to ConceptNet (ablation) | VK-OOD · OKVQA | accuracy: 51.1 -> 52.4 | Improved |
| 30% incomplete knowledge triplets | VK-OOD · OKVQA | accuracy: 52.4 -> 51.2 | Hurt |
| add OOD layer to ITM-only pretraining (ablation) | VK-OOD · Flickr30k zero-shot | TR@1: 82.1 -> 84.5 | Improved |
| add OOD layer to ITM+MLM pretraining (ablation) | VK-OOD · Flickr30k zero-shot | IR@1: 74.1 -> 77.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FLAVA — FLAVA: A Foundational Language and Vision Alignment Model (CVPR 2022) · better on 2 of 2 shared results
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
- Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation (NeurIPS 2025 · similarity 0.88)
- Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations (CVPR 2025 · similarity 0.87)
- Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity (ICML 2024 · similarity 0.87)
- Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection (ICLR 2025 · similarity 0.87)
- MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities (NeurIPS 2024 · similarity 0.86)
- RUNA: Object-Level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations (AAAI 2025 · similarity 0.86)
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.
