AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Deep Quantization: Encoding Convolutional Activations With Deep Generative Model

Zhaofan Qiu, Ting Yao, Tao Mei

CVPR 2017 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 75 citations (OpenAlex)

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 changedWhereMeasuredEffect
Replace GMM Fisher Vector quantization with FV-VAEVGG_19 pool5 representations · UCF101 split1accuracy: 78.85% -> 83.45%Improved
Add classification loss to FV-VAE training (ablation)VGG_19 pool5 · UCF101 split1accuracy: 81.91% -> 83.45%Improved
Use ResNet_152 res5c activations instead of VGG_19 pool5 (ablation)FV-VAE · UCF101 split1accuracy: 83.45% -> 86.33%Improved
Fine-tune VGG_19 on UCF101 before FV-VAE encoding (ablation)FV-VAE · UCF101 split1accuracy: 83.45% -> 82.13%Hurt
Combine frame and optical-flow FV-VAE representations (ablation)FV-VAE-pool5 · UCF101 (3 splits, ×10 augmentation)accuracy: 83.9% -> 93.7%Improved
Use ResNet_152 res5c in the fused frame and optical-flow system (ablation)FV-VAE with pool5 optical flow · UCF101 (3 splits, ×10 augmentation)accuracy: 93.7% -> 94.2%Improved
Add IDT features to the fused FV-VAE system (ablation)FV-VAE-(res5c + pool5 optical flow) · UCF101 (3 splits, ×10 augmentation)accuracy: 94.2% -> 95.2%Improved
Replace VGG_19 pool5 GA with FV-VAE-res5cActivityNet v1.3 validation · ActivityNet v1.3 validationmAP: 76.56% -> 84.09%Improved
Add VGG_19 fine-tuning on CUB-200-2011 (ablation)FV-VAE · CUB-200-2011 test, w/o fine-tuningaccuracy: 79.3% -> 82.4%Improved
Add bounding-box information at training and test time (ablation)FV-VAE with fine-tuned VGG_19 · CUB-200-2011 testaccuracy: 82.4% -> 83.6%Improved
Increase representation dimension (ablation)FV-VAE · UCF101 split1accuracyImproved
Vary the classification-loss weight λ₃ (ablation)FV-VAE · UCF101 split1accuracyMixed

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