OpenGVLab / OpenGVLab/InternVideo

Attention-Guided Token Selection Algorithm in InternVideo 2.5

Open
#302 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.4k
Forks
160
PR merge metrics
No merged PRs in 30d

Description

Hi OpenGVLab team, thank you very much for all your excellent models.

In the InternVideo 2.5 paper section 3.1, it is mentioned that:

(1) uniform token pruning in early layers to maintain structural integrity while reducing computational overhead, and (2) attention-guided token selection in deeper layers to retain task-relevant essences.

Regarding the second point, attention-guided token selection, could you please share the specific method you used? Since this process involves attention weight, it may not be compatible with Flash Attention 2. Does this lead to excessive memory consumption?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue identifies InternVideo 2.5 paper section 3.1 as the starting point; review that section and locate the corresponding implementation in the repository. Done would mean documenting the attention-guided token-selection method and addressing its compatibility with Flash Attention 2 and its memory implications.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.