AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Factors of Transferability for a Generic ConvNet Representation

Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson

TPAMI 2016 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 327 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
optimize all transferability factors vs standard FC6 representationMedium AlexNet ConvNet + linear SVM · VOC07accuracy (%): 71.8 -> 80.7Improved
optimize all transferability factors vs standard FC6 representationMedium AlexNet ConvNet · Petaccuracy (%): 78.5 -> 88.1Improved
optimize all transferability factors vs standard FC6 representationMedium AlexNet ConvNet · UKBscore: 93.0 -> 96.3Improved
optimize factors vs standard (non-ConvNet state of the art stays better)Deep Optimized · Oxford buildings retrievalmAP (%): 81.7 non-ConvNet vs 79.0 optimizedMixed
add fine-tuning to the ConvNet (ablation)Medium FC7 · CUBaccuracy (%): 62.9 -> 66.4Improved
add fine-tuning to the ConvNet (ablation)Medium FC7 · MITaccuracy (%): 65.9 -> 66.3Improved
add fine-tuning to the ConvNet (ablation)Medium FC7 · Floweraccuracy (%): 90.4 -> 91.4Improved
train on Places scene labels instead of ImageNet (ablation)AlexNet-style ConvNet · Petaccuracy (%): 78.4 -> 49.9Hurt
train on Places scene labels instead of ImageNet (ablation)AlexNet-style ConvNet · MITaccuracy (%): 64.9 -> 69.3Improved
concatenate ImageNet and Places features (ablation)ImageNet ConvNet · VOC07accuracy (%): 71.6 -> 73.8Improved
train on more source images (SUN397 130K to Places 2.5M) (ablation)scene ConvNet · MITaccuracy (%): 62.6 -> 69.3Improved
fine-tune with extra Pet and CUB images in addition to VOC (ablation)ConvNet detector · VOC07 catmAP (%): 60.7 -> 63.0Improved

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