AI Paper Atlas

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

Towards In-context Scene Understanding

Ivana Balazevic, David Steiner, Nikhil Parthasarathy, Relja Arandjelovic, Olivier J Henaff

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 6 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
add memory contextualization (cont.) to MoCLR (ablation)MoCLR · PASCAL VOC (NN retrieval)mIoU: 38.6 -> 55.6Improved
add memory contextualization (cont.) to MoCLR (ablation)MoCLR · ADE20K (NN retrieval)mIoU: 4.9 -> 15.3Improved
replace mean pooling with [CLS] pooling (ablation)MoCLR · PASCAL VOC (NN retrieval)mIoU: 38.6 -> 64.5Improved
add contextualization on top of [CLS] pooling (ablation)MoCLR + [CLS] · PASCAL VOC (NN retrieval)mIoU: 64.5 -> 65.6Improved
use QK attention pooling plus contextualization instead of [CLS] (ablation)MoCLR + cont. · PASCAL VOC (NN retrieval)mIoU: 65.6 -> 68.7Improved
add a value head (QKV att.) to QK attention pooling and contextualization (ablation)Hummingbird · PASCAL VOC (NN retrieval)mIoU: 68.7 -> 70.5Improved
remove contextualization from QKV attention pooling (ablation)Hummingbird · PASCAL VOC (NN retrieval)mIoU: 70.5 -> 68.0Hurt
add retrieval-based supervision (Hummingbird++)Hummingbird ViT-B IN1K · PASCAL VOC (NN retrieval)mIoU: 70.5 -> 72.1Improved
add retrieval-based supervision (Hummingbird++)Hummingbird ViT-B IN1K · NYUv2 depth (NN retrieval)RMSE: .718 -> .738Hurt
scale pretraining data from IN1K to IN22KHummingbird ViT-B · PASCAL VOC (NN retrieval)mIoU: 70.5 -> 73.5Improved
scale pretraining data from IN1K to IN22KMAE ViT-B · PASCAL VOC (NN retrieval)mIoU: 6.6 -> 9.8No clear effect
scale encoder from ViT-B to ViT-LHummingbird IN22K · PASCAL VOC (NN retrieval)mIoU: 73.5 -> 76.9Improved

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