Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yan, Rui, Wang, Jin, Qu, Hongyu, Du, Xiaoyu, Zhang, Dong, Tang, Jinhui, Tan, Tieniu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2502.00426
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910819892068352
author Yan, Rui
Wang, Jin
Qu, Hongyu
Du, Xiaoyu
Zhang, Dong
Tang, Jinhui
Tan, Tieniu
author_facet Yan, Rui
Wang, Jin
Qu, Hongyu
Du, Xiaoyu
Zhang, Dong
Tang, Jinhui
Tan, Tieniu
contents Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class names with generated visual samples (support-set) has shown promising results. However, TPT cannot avoid the semantic gap between modalities while the support-set cannot be tuned. To this end, we draw on each other's strengths and propose a novel framework namely TEst-time Support-set Tuning for zero-shot Video Classification (TEST-V). It first dilates the support-set with multiple prompts (Multi-prompting Support-set Dilation, MSD) and then erodes the support-set via learnable weights to mine key cues dynamically (Temporal-aware Support-set Erosion, TSE). Specifically, i) MSD expands the support samples for each class based on multiple prompts enquired from LLMs to enrich the diversity of the support-set. ii) TSE tunes the support-set with factorized learnable weights according to the temporal prediction consistency in a self-supervised manner to dig pivotal supporting cues for each class. $\textbf{TEST-V}$ achieves state-of-the-art results across four benchmarks and has good interpretability for the support-set dilation and erosion.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00426
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification
Yan, Rui
Wang, Jin
Qu, Hongyu
Du, Xiaoyu
Zhang, Dong
Tang, Jinhui
Tan, Tieniu
Computer Vision and Pattern Recognition
Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class names with generated visual samples (support-set) has shown promising results. However, TPT cannot avoid the semantic gap between modalities while the support-set cannot be tuned. To this end, we draw on each other's strengths and propose a novel framework namely TEst-time Support-set Tuning for zero-shot Video Classification (TEST-V). It first dilates the support-set with multiple prompts (Multi-prompting Support-set Dilation, MSD) and then erodes the support-set via learnable weights to mine key cues dynamically (Temporal-aware Support-set Erosion, TSE). Specifically, i) MSD expands the support samples for each class based on multiple prompts enquired from LLMs to enrich the diversity of the support-set. ii) TSE tunes the support-set with factorized learnable weights according to the temporal prediction consistency in a self-supervised manner to dig pivotal supporting cues for each class. $\textbf{TEST-V}$ achieves state-of-the-art results across four benchmarks and has good interpretability for the support-set dilation and erosion.
title TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.00426