AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation

Yanyuan Qiao, Zheng Yu, Qi Wu

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 27 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 CIB (cross-modal interaction booster) to head-only tuning (ablation)HAMT head tuning · REVERIE Val UnseenSPL: 15.19 -> 21.62Improved
Add LEA (language encoder adapter) to head tuning (ablation)HAMT head tuning · REVERIE Val UnseenSPL: 15.19 -> 18.21Improved
Add LoRA to LEA+HIB+CIB (ablation)VLN-PETL · REVERIE Val UnseenSPL: 26.51 -> 27.67Improved
Use CIB instead of cross-modal adapter (CEA) (ablation)VLN-PETL · REVERIE Val UnseenSPL: 20.77 -> 21.62Improved
Use HIB instead of history adapter (HEA) (ablation)VLN-PETL · REVERIE Val UnseenSPL: SPL 18.98 -> 18.49; RGSPL 8.39 -> 9.32Mixed
Use learnable gate alpha instead of fixed 0.5 (ablation)HIB and CIB gates · REVERIE Val UnseenRGSPL: 14.50 -> 15.96Improved
Set gate temperature T to 0.1 versus 1 (ablation)HIB and CIB gates · REVERIE Val UnseenSPL: 27.67 vs 27.81No clear effect
Use BitFit or Prompt Tuning instead of Adapter/LoRA for VLNHAMT · RxR Val UnseennDTW: BitFit 50.47, Prompt Tuning 44.94 vs Adapter 63.56Hurt
Use VLN-PETL (2.82% params) instead of full fine-tuningHAMT · R2R Val UnseenSR: 64.24 -> 65.47Improved
Use VLN-PETL instead of full fine-tuning on REVERIEHAMT · REVERIE Val UnseenSPL: 28.92 -> 27.67Hurt

Later papers that compared with this method

2 later accepted papers report VLN-PETL as a baseline in their results tables; 2 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