Research map / Detection and segmentation / Open-set and few-shot detection
Feature Deformation Meta-Networks in Image Captioning of Novel Objects
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 augmented feature-text pairs from FDM-net to training (ablation) | general captioning model · NOC split out-of-domain test | F1: 0 -> 85.7 | Helped |
| add FDM-net augmentation (1000 pairs, MLS+SGSR+CBS) (ablation) | general captioning model · NOC split out-of-domain test | CIDEr: 65.2 -> 85.3 | Helped |
| add FDM-net augmentation (ablation) | general captioning model · NOC split in-domain test | CIDEr: 105.1 -> 105.5 | No clear effect |
| add constrained beam search at test time (ablation) | FDM-net (1000 pairs) · NOC split out-of-domain test | F1: 64.7 -> 85.7 | Helped |
| increase augmented pairs from 1000 to 1500 (ablation) | FDM-net MLS+SGSR+CBS · NOC split out-of-domain test | CIDEr: 85.3 -> 83.9 | Hurt |
| increase augmented pairs from 1000 to 1500 (ablation) | FDM-net MLS+SGSR+CBS · NOC split out-of-domain test | F1: 85.7 -> 87.0 | Helped |
| human preference vs NBT on word incorporation | FDM-net · MSCOCO out-of-domain human eval | preference %: 50.0 vs 18.0 | Helped |
Closest papers by meaning
- Image Deformation Meta-Networks for One-Shot Learning (CVPR 2019 · similarity 0.90)
- Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects (CVPR 2017 · similarity 0.88)
- Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning (AAAI 2019 · similarity 0.87)
- Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning (CVPR 2022 · similarity 0.87)
- Relational Distant Supervision for Image Captioning without Image-Text Pairs (AAAI 2024 · similarity 0.86)
- Composing Object Relations and Attributes for Image-Text Matching (CVPR 2024 · 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.