AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

The Unreasonable Effectiveness of Large Language-Vision Models for Source-Free Video Domain Adaptation

Giacomo Zara, Alessandro Conti, Subhankar Roy, Stéphane Lathuilière, Paolo Rota, Elisa Ricci

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 22 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 zero-shot CLIP ViT-B/32 instead of best SFVUDA methodSFVUDA · Daily-DAaccuracy (%): 39.6 -> 48.1Improved
add unsupervised target adapter trained on CLIP pseudo-labels (ablation)zero-shot CLIP · Daily-DAaccuracy (%): 48.1 -> 50.8Improved
ensemble CLIP, source and target adapters (ablation)zero-shot CLIP · Daily-DAaccuracy (%): 48.1 -> 53.8Improved
ensemble CLIP, source and target adapters (ablation)zero-shot CLIP · UCF-HMDB_fullaccuracy (%): 89.7 -> 92.6Improved
use source adapter alone instead of CLIP (ablation)zero-shot CLIP · Daily-DAaccuracy (%): 48.1 -> 41.5Hurt
increase number of text templates from 1 to 12 (ablation)DALL-V inference · Daily-DA, UCF-HMDB_fullaccuracyImproved
increase templates beyond 12 (ablation)DALL-V inference · Daily-DA, UCF-HMDB_fullaccuracyNo clear effect
fine-tune full vision encoder instead of adapter in distillation (ablation)DALL-V student · UCF-HMDB_fullaccuracy (%): 91.0 -> 91.8Mixed
use original CLIP prompts instead of short action-oriented prompts (ablation)zero-shot CLIP pseudo-labelling · UCF-HMDB_fullaccuracy (%): 89.7 -> 83.2Hurt
replace 'video' with 'image' in prompts (ablation)zero-shot CLIP · UCF-HMDB_fullaccuracy (%): 89.7 -> 89.8No clear effect
DALL-V versus EXTERN on Sports-DASFVUDA · Sports-DAaccuracy (%): 83.2 -> 82.3Hurt

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