Research map / Detection and segmentation / Open-set and few-shot detection
Context-Aware Zero-Shot Recognition
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 discriminability objective with λ=1 to CIDEr training (ablation) | CIDEr captioning model · Test set | CIDEr: 1.2604 -> 1.2770 | Helped |
| Add discriminability objective with λ=1 to CIDEr training (ablation) | CIDEr captioning model · Test set | SPICE: 0.2260 -> 0.2302 | Helped |
| Add discriminability objective with λ=1 to CIDEr training (ablation) | CIDEr captioning model · Test set | BLEU4: 0.5971 -> 0.3971 | Hurt |
| Increase discriminability weight from λ=1 to λ=10 (ablation) | CIDEr captioning model · Test set | Acc: 72.63% -> 79.75% | Helped |
| Increase discriminability weight from λ=1 to λ=10 (ablation) | CIDEr captioning model · Test set | BLEU4: 0.3971 -> 0.3538 | Hurt |
| Increase discriminability weight from λ=1 to λ=10 (ablation) | CIDEr captioning model · Test set | CIDEr: 1.2770 -> 1.1429 | Hurt |
| Add discriminability objective with λ=1 (ablation) | Attention captioning model trained with CIDEr · Validation set | BLEU4: 0.3592 -> 0.3627 | Helped |
| Increase discriminability weight from λ=1 to λ=10 (ablation) | Attention captioning model trained with CIDEr · Validation set | Acc: 75.74% -> 83.50% | Helped |
| Increase discriminability weight from λ=1 to λ=10 (ablation) | Attention captioning model trained with CIDEr · Validation set | CIDEr: 1.1406 -> 1.0552 | Hurt |
| Add discriminability objective with λ=1 (ablation) | Fully connected captioning model trained with CIDEr · Validation set | CIDEr: 1.0154 -> 1.0231 | Helped |
| Increase discriminability weight from λ=1 to λ=10 (ablation) | Fully connected captioning model trained with CIDEr · Validation set | Acc: 79.26% -> 88.69% | Helped |
| Increase discriminability weight from λ=1 to λ=10 (ablation) | Fully connected captioning model trained with CIDEr · Validation set | CIDEr: 1.0231 -> 0.8795 | Hurt |
Closest papers by meaning
- Context-Aware Zero-Shot Learning for Object Recognition (ICML 2019 · similarity 0.94)
- Zero-Shot Recognition Using Dual Visual-Semantic Mapping Paths (CVPR 2017 · similarity 0.90)
- Zero-Shot Classification With Discriminative Semantic Representation Learning (CVPR 2017 · similarity 0.89)
- Robust Region Feature Synthesizer for Zero-Shot Object Detection (CVPR 2022 · similarity 0.88)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.88)
- Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions (CVPR 2024 · 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.