AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

MixFormerV2: Efficient Fully Transformer Tracking

Yutao Cui, Tianhui Song, Gangshan Wu, Limin Wang

NeurIPS 2023 · Architectures and efficiency › Attention and transformers · approach: Transformer block and depth design · 32 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 4 distribution-regression prediction tokens instead of a single-token direct box (ablation)MixFormerV2 (12-layer) · LaSOTAUC: 63.1% -> 67.5%Improved
add token-based score head (ablation)MixFormerV2-B · LaSOTAUC: 68.9% -> 70.6%Improved
dense-to-sparse distillation from MixViT-B (ablation)MixFormerV2 12-layer · LaSOTAUC: 67.5% -> 68.9%Improved
use larger MixViT-L teacher instead of MixViT-B (ablation)MixFormerV2 12-layer · LaSOTAUC: 68.9% -> 69.6%Improved
add logits distillation (ablation)4-layer MixViT student · LaSOTAUC: 60.7% -> 62.4%Improved
add feature mimicking on top of logits distillation (ablation)4-layer MixViT student · LaSOTAUC: 62.4% -> 62.9%Improved
progressive model depth pruning init instead of MAE first 4 layers (ablation)4-layer student · LaSOTAUC: 62.9% -> 64.8%Improved
add intermediate teacher (ablation)4-layer student · LaSOTAUC: 64.8% -> 65.5%Improved
vary eliminating epochs m from 40 to 50 (ablation)MixFormerV2-B · LaSOTAUC: 68.5% -> 68.5%No clear effect
prune 12 layers to 8 layers (ablation)MixFormerV2-B · LaSOTAUC: 68.9% -> 68.5%Hurt
reduce MLP ratio 4 to 1 (ablation)4-layer MixFormerV2-S · LaSOTAUC: 61.0% -> 59.4%Hurt

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