AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Hardware Resilience Properties of Text-Guided Image Classifiers

Syed Talal Wasim, Kabila Haile Soboka, Abdulrahman Mahmoud, Salman Khan, David Brooks, Gu-Yeon Wei

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 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
Initialize projection layer with CLIP embeddings of GPT-3 descriptions (ablation)ResNet-50 · ImageNet vallast-layer reliability improvement: 6.09x vs baseline (random init 1.74x)Improved
Use hand-crafted CLIP prompt init instead of random init (ablation)ResNet-50 · ImageNet vallast-layer reliability improvement: 1.74 -> 5.06Improved
Use GPT-3 descriptions instead of simple CLIP prompt for init (ablation)ResNet-50 · ImageNet vallast-layer reliability improvement: 5.06 -> 6.09Improved
Use GPT-3 descriptions instead of simple CLIP prompt for init (ablation)ResNet-50 · ImageNet valreliability improvement across backbone: 3.28 -> 3.93Improved
Random init of projection layer still gives some gain (ablation)ResNet-50 · ImageNet vallast-layer reliability improvement: 1.09 across backbone, 1.74 last layerMixed
Apply text-guided classifier across backbonesVGG family · ImageNet vallast-layer reliability improvement: 13.68x averageImproved
Apply text-guided classifier across backbonesResNet family · ImageNet vallast-layer reliability improvement: 4.01x averageImproved
Apply text-guided classifier to Swin-V2-TSwin-V2-T · ImageNet valoverall reliability improvement: 1.07xNo clear effect
Apply text-guided classifierResNet-101 · ImageNet valtop-1 accuracy: 77.25 -> 75.52Hurt
Apply text-guided classifierMaxViT-T · ImageNet valtop-1 accuracy: 82.98 -> 83.08No clear effect
Apply text-guided classifierResNet-50 · ImageNet valTop2Diff: 70.32 -> 73.67Improved
Apply text-guided classifier on CIFAR100FocalNet-T · CIFAR100top-1 accuracy: 77.06 -> 79.21Improved

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