AI Paper Atlas

Research map / Architectures and efficiency / CNN design

FTL: A universal framework for training low-bit DNNs via Feature Transfer

Kunyuan Du, Ya Zhang, Haibing Guan, Qi Tian, Shenggan Cheng, James Lin

ECCV 2020 · Architectures and efficiency › CNN design · approach: Invertible and wide-network analysis · 1 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
use centered cosine distance in continuous space (ablation)FTL (BNN) · CIFAR-10 (BNN)accuracy gain: +0.84%Improved
use L1 norm in continuous space instead of centered cosine distance (ablation)FTL (BNN) · CIFAR-10 (BNN)accuracy gain: +0.45%Improved
apply L1 norm in discrete space (quantize 32-bit features first) (ablation)FTL (BNN) · CIFAR-10 (BNN)accuracy gain: -0.07%No clear effect
gradient rescaling with intermediate w (0.002) instead of teacher-student w=1e-5 (ablation)FTL (BNN) · CIFAR-10 (VGG-small 0.5x)accuracy gain: -0.04% -> +0.29%Improved
mutual learning mode (w=0.5) instead of gradient rescaling with small w (ablation)FTL (BNN) · CIFAR-10 (VGG-small 0.5x)accuracy gain: +0.29% -> -0.61%Hurt
add FTL to fine-tuning from pretrained 32-bit DNN (ablation)FTL (BNN) · CIFAR-10 (VGG-small)Validation accuracy: 89.31 -> 89.62Improved
add FTL to logits transfer (ablation)FTL (BNN) · CIFAR-10 (VGG-small)Validation accuracy: 89.49 -> 89.96Improved
replace JGT feature guidance with FTLFTL (BNN) · CIFAR-10 (BNN ResNet-small)Top-1 accuracy: 88.89 -> 90.88Improved
replace JGT feature guidance with FTLFTL (BNN) · CIFAR-10 (BNN VGG-small)Top-1 accuracy: 89.10 -> 89.82Improved
replace JGT* with FTLDoReFa-Net AlexNet · ImageNet (DoReFa AlexNet)Top-1 accuracy: 51.6 -> 54.0Improved
add FTL with 4-bit quantized gradientsDoReFa-Net AlexNet · ImageNet (DoReFa AlexNet 1/2/4)Top-1 accuracy: 41.5 -> 44.9Improved
add FTL to LQ-NetLQ-Net ResNet-50 · ImageNet (ResNet-50 1/2/32)Top-1 accuracy: 68.7 -> 69.6Improved

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