paper-with-me

홈 › Papers

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

2024-12-17 · Mark Endo, Xiaohan Wang, Serena Yeung-Levy

Recent works on accelerating Vision-Language Models show that strong performance can be maintained across a variety of vision-language tasks despite highly compressing visual information. In this work, we examine the popular acceleration approach of early pruning of visual tokens inside the language model and find that its strong performance across many tasks is not due to an exceptional ability to compress visual information, but rather the benchmarks' limited ability to assess fine-grained visual capabilities. Namely, we demonstrate a core issue with the acceleration approach where most tokens towards the top of the image are pruned away. Yet, this issue is only reflected in performance for a small subset of tasks such as localization. For the other evaluated tasks, strong performance is maintained with the flawed pruning strategy. Noting the limited visual capabilities of the studied acceleration technique, we propose FEATHER (Fast and Effective Acceleration wiTH Ensemble cRiteria), a straightforward approach that (1) resolves the identified issue with early-layer pruning, (2) incorporates uniform sampling to ensure coverage across all image regions, and (3) applies pruning in two stages to allow the criteria to become more effective at a later layer while still achieving significant speedup through early-layer pruning. With comparable computational savings, we find that FEATHER has more than $5\times$ performance improvement on the vision-centric localization benchmarks compared to the original acceleration approach.

📄 PDF Abstract BibTeX arXiv:2412.13180

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models

2026-05-27 · Landi He, Mingde Yao, Shawn Young, Lijian Xu arxiv

Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rely on Gumbel-Softmax to approximate discrete selection during trainin…

Continuous Control

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

2025-10-03 · Xin Zou, Di Lu, Yizhou Wang, Yibo Yan 외 arxiv

Despite their powerful capabilities, Multimodal Large Language Models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens. Recent studies have explored token pruning to …

Feather: An Elegant Solution to Effective DNN Sparsification

2023-10-03 · Athanasios Glentis Georgoulakis, George Retsinas, Petros Maragos

Neural Network pruning is an increasingly popular way for producing compact and efficient models, suitable for resource-limited environments, while preserving high performance. While the pruning can be performed using a …

Network Pruning

Feathers dataset for Fine-Grained Visual Categorization

2020-04-18 · Alina Belko, Konstantin Dobratulin, Andrey Kuznetsov

This paper introduces a novel dataset FeatherV1, containing 28,272 images of feathers categorized by 595 bird species. It was created to perform taxonomic identification of bird species by a single feather, which can be …

Fine-Grained Visual CategorizationFine-Grained Visual Recognition

Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models

2025-03-22 · Wenqi Pei, Hailing Xu, Hengyuan Zhao, Shizheng Hou 외

Natural Language to SQL (NL2SQL) has seen significant advancements with large language models (LLMs). However, these models often depend on closed-source systems and high computational resources, posing challenges in dat…