AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

Lijun Yu, Yong Cheng, Zhiruo Wang, Vivek Kumar, Wolfgang Macherey, Yanping Huang, David A Ross, Irfan Essa, Yonatan Bisk, Ming-Hsuan Yang, Kevin Patrick Murphy, Alexander G Hauptmann and 1 more

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 7 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 SPAE lexical tokens instead of LQAE tokensGPT 3.5 few-shot classification · mini-ImageNet 2-way classificationaverage accuracy: 53.97 -> 69.51Improved
Use SPAE lexical tokens instead of LQAE tokensGPT 3.5 few-shot classification · mini-ImageNet 5-way classificationaverage accuracy: 29.04 -> 53.91Improved
Use SPAE with PaLM 2 rather than Frozenfew-shot VQA · Real-Fast-VQA, 1 inner shotVQA performance: 7.8 -> 14.3Improved
Replace the learned codebook with a frozen language codebook (ablation)SPAE tokenizer · ImageNet ILSVRC2012 128×128FID: 5.48 -> 7.44Hurt
Add semantic loss to the frozen codebook (ablation)SPAE tokenizer · ImageNet ILSVRC2012 128×128FID: 7.44 -> 5.17Improved
Use 2-layer RQ with the frozen codebook (ablation)SPAE tokenizer · ImageNet ILSVRC2012 128×128FID: 5.17 -> 11.94Hurt
Use 2-layer SAQ instead of 2-layer RQ (ablation)SPAE tokenizer · ImageNet ILSVRC2012 128×128FID: 11.94 -> 12.30Hurt
Add six-layer pyramid SAQ (ablation)SPAE tokenizer · mini-ImageNet 5-way 1-shotclassification accuracy: 46.2 -> 65.1Improved
Remove per-layer semantic thresholds (ablation)SPAE · ImageNet ILSVRC2012 128×128FID: 4.41 -> 4.33Improved
Remove dynamic semantic loss weight (ablation)SPAE · ImageNet ILSVRC2012 128×128FID: 4.41 -> 9.00Hurt
Remove perceptual loss (ablation)SPAE · ImageNet ILSVRC2012 128×128FID: 4.41 -> 40.47Hurt
Remove perceptual loss (ablation)SPAE · mini-ImageNet 5-way 1-shotclassification accuracy: 65.1 -> 69.5Improved

Later papers that compared with this method

1 later accepted paper reports SPAE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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