AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Generating Features With Increased Crop-Related Diversity for Few-Shot Object Detection

Jingyi Xu, Hieu Le, Dimitris Samaras

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 52 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add vanilla conditional-VAE generated featuresDeFRCN · PASCAL VOC Novel Split 1, 1-shotnAP50: 56.3 -> 60.0Improved
Control generated crop variation by rescaling latent-code norm according to crop IoU (ablation)DeFRCN with VAE-generated features · PASCAL VOC Novel Split 1, 1-shotnAP50: 60.0 -> 62.1Improved
Add Norm-VAE generated featuresDeFRCN · MS COCO novel classes, 1-shotnAP: 6.6 -> 9.5Improved
Add crop-diverse generated featuresDeFRCN · PASCAL VOC Novel Split 1, 1-shot hard proposalsAP50–75: 16.6 -> 18.8Improved
Train vanilla VAE on augmented rather than original data (ablation)Vanilla-VAE feature generation · PASCAL VOC Novel Split 1, 1-shotnAP50: 60.0 -> 60.1No clear effect
Use only low-IoU/harder generated features instead of diverse feature norms (ablation)Norm-VAE training of DeFRCN · PASCAL VOC Novel Split 1, 1-shotnAP50: 60.2 vs 60.9Improved
Use only high-IoU/easier generated features instead of diverse feature norms (ablation)Norm-VAE training of DeFRCN · PASCAL VOC Novel Split 1, 1-shotnAP75: 30.5 vs 31.6Improved
Use only one difficulty group of generated features rather than varied norms (ablation)Norm-VAE training of DeFRCN · PASCAL VOC Novel Split 1nAP50Hurt
Use Word2Vec rather than CLIP semantic embeddings (ablation)Norm-VAE · PASCAL VOC Novel Split 1, 1-shotnAP50: 62.1 -> 61.6Hurt
Replace latent-norm control with β-VAE latent-dimension traversal (ablation)DeFRCN with generated features · PASCAL VOC Novel Split 1, 1-shotnAP50: 62.1 -> 61.3Hurt
Replace latent-norm control with CSVAE latent-subspace manipulation (ablation)DeFRCN with generated features · PASCAL VOC Novel Split 1, 1-shotnAP50: 62.1 -> 61.6Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy