AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Domain-Adaptive Deep Network Compression

Marc Masana, Joost van de Weijer, Luis Herranz, Andrew D. Bagdanov, Jose M. Alvarez

ICCV 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 56 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 activation-aware DALR instead of weight-only truncated SVDfc6 low-rank compression · CUB-200 Birds (k=32)accuracy: 16.83 -> 48.81Improved
use DALR instead of truncated SVDfc6 low-rank compression · Oxford 102 Flowers (k=32)accuracy: 14.00 -> 72.17Improved
use DALR instead of truncated SVDfc6 low-rank compression · Stanford 40 Actions (k=32)accuracy: 38.18 -> 64.70Improved
use DALR instead of truncated SVDfc7 low-rank compression · Oxford 102 Flowers (k=32)accuracy: 58.14 -> 72.32Improved
use DALR instead of truncated SVD on the source domainfc6 low-rank compression · ImageNet val (k=32)top-1 error: 79.44 -> 66.43Improved
use DALR instead of truncated SVD on the source domainfc7 low-rank compression · ImageNet val (k=32)top-1 error: 57.07 -> 56.32No clear effect
add bias compensation to truncated SVD (ablation)fc6 low-rank compression · CUB-200 Birds (k=32)accuracy: 16.83 -> 27.91Improved
add bias compensation to truncated SVD (ablation)fc6 low-rank compression · Stanford 40 Actions (k=32)accuracy: 38.18 -> 46.76Improved
add bias compensation to truncated SVD (ablation)fc7 low-rank compression · Oxford 102 Flowers (k=32)accuracy: 58.14 -> 57.07Hurt
add bias compensation to truncated SVD (ablation)fc7 low-rank compression · ImageNet val (k=32)top-1 error: 57.07 -> 55.57Improved
add bias compensation on top of DALR (ablation)DALR · fine-tuned VGG19 compressionaccuracyNo clear effect
replace truncated SVD with activation-based pruning (mean)fc6 compression · CUB-200 Birds (k=1024)accuracy: 55.25 -> 50.41Hurt

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