Files
陈赣 06f1fd69a6
Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
first commit
2026-06-05 16:53:03 +08:00

2.8 KiB

Video Vision Transformer (ViViT) video-vision-transformer-vivit

개요 overview

Vivit 모델은 Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lučić, Cordelia Schmid가 제안한 논문 ViViT: A Video Vision Transformer에서 소개되었습니다. 이 논문은 비디오 이해를 위한 pure-transformer 기반의 모델 집합 중에서 최초로 성공한 모델 중 하나를 소개합니다.

논문의 초록은 다음과 같습니다:

우리는 이미지 분류에서 최근 성공을 거둔 순수 트랜스포머 기반 모델을 바탕으로 비디오 분류를 위한 모델을 제안합니다. 본 모델은 입력 비디오로부터 시공간 토큰을 추출한 후, 이를 일련의 트랜스포머 레이어로 인코딩합니다. 비디오에서 발생하는 긴 토큰 시퀀스를 처리하기 위해, 입력의 공간 및 시간 차원을 분리하는 여러 효율적인 모델 변형을 제안합니다. 트랜스포머 기반 모델은 대규모 학습 데이터셋에서만 효과적이라는 것이 일반적이지만, 우리는 학습 중 모델을 효과적으로 정규화하고, 사전 학습된 이미지 모델을 활용함으로써 상대적으로 작은 데이터셋에서도 학습할 수 있는 방법을 보여줍니다. 또한, 철저한 소거(ablation) 연구를 수행하고 Kinetics 400 및 600, Epic Kitchens, Something-Something v2, Moments in Time을 포함한 여러 비디오 분류 벤치마크에서 최첨단 성과를 달성하여, 기존의 3D 합성곱 신경망 기반 방법들을 능가합니다.

이 모델은 jegormeister가 기여하였습니다. 원본 코드(JAX로 작성됨)는 여기에서 확인할 수 있습니다.

VivitConfig transformers.VivitConfig

autodoc VivitConfig

VivitImageProcessor transformers.VivitImageProcessor

autodoc VivitImageProcessor - preprocess

VivitModel transformers.VivitModel

autodoc VivitModel - forward

VivitForVideoClassification transformers.VivitForVideoClassification

autodoc transformers.VivitForVideoClassification - forward