2022-12-09 更新
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Authors:Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Lu Yuan, Yu-Gang Jiang
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like raw pixel RGB values. In this paper, we propose masked video distillation (MVD), a simple yet effective two-stage masked feature modeling framework for video representation learning: firstly we pretrain an image (or video) model by recovering low-level features of masked patches, then we use the resulting features as targets for masked feature modeling. For the choice of teacher models, we observe that students taught by video teachers perform better on temporally-heavy video tasks, while image teachers transfer stronger spatial representations for spatially-heavy video tasks. Visualization analysis also indicates different teachers produce different learned patterns for students. Motivated by this observation, to leverage the advantage of different teachers, we design a spatial-temporal co-teaching method for MVD. Specifically, we distill student models from both video teachers and image teachers by masked feature modeling. Extensive experimental results demonstrate that video transformers pretrained with spatial-temporal co-teaching outperform models distilled with a single teacher on a multitude of video datasets. Our MVD with vanilla ViT achieves state-of-the-art performance compared with previous supervised or self-supervised methods on several challenging video downstream tasks. For example, with the ViT-Large model, our MVD achieves 86.4% and 75.9% Top-1 accuracy on Kinetics-400 and Something-Something-v2, outperforming VideoMAE by 1.2% and 1.6% respectively. Code will be available at \url{https://github.com/ruiwang2021/mvd}.
PDF
点此查看论文截图
Learning Domain Invariant Prompt for Vision-Language Models
Authors:Cairong Zhao, Yubin Wang, Xinyang Jiang, Yifei Shen, Kaitao Song, Dongsheng Li, Duoqian Miao
Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples. However, although prompt learning achieves excellent performance over in-domain data, it still faces the major challenge of generalizing to unseen classes and domains. Some existing prompt learning methods tackle this issue by adaptively generating different prompts for different tokens or domains but neglecting the ability of learned prompts to generalize to unseen domains. In this paper, we propose a novel prompt learning paradigm that directly generates domain invariant prompt generalizable to unseen domains, called MetaPrompt. Specifically, a dual-modality prompt tuning network is proposed to generate prompts for inputs from both image and text modalities. More importantly, we propose a meta-learning-based prompt tuning algorithm that explicitly constrains the prompt tuned on a specific domain or class also to achieve good performance on another domain or class. Extensive experiments on 11 datasets for base-to-new generalization and four datasets for domain generalization demonstrate that our method consistently and significantly outperforms existing methods.
PDF 13 pages, 3 figures, 4 tables
点此查看论文截图
Group Generalized Mean Pooling for Vision Transformer
Authors:Byungsoo Ko, Han-Gyu Kim, Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Geonmo Gu, Wonjae Kim
Vision Transformer (ViT) extracts the final representation from either class token or an average of all patch tokens, following the architecture of Transformer in Natural Language Processing (NLP) or Convolutional Neural Networks (CNNs) in computer vision. However, studies for the best way of aggregating the patch tokens are still limited to average pooling, while widely-used pooling strategies, such as max and GeM pooling, can be considered. Despite their effectiveness, the existing pooling strategies do not consider the architecture of ViT and the channel-wise difference in the activation maps, aggregating the crucial and trivial channels with the same importance. In this paper, we present Group Generalized Mean (GGeM) pooling as a simple yet powerful pooling strategy for ViT. GGeM divides the channels into groups and computes GeM pooling with a shared pooling parameter per group. As ViT groups the channels via a multi-head attention mechanism, grouping the channels by GGeM leads to lower head-wise dependence while amplifying important channels on the activation maps. Exploiting GGeM shows 0.1%p to 0.7%p performance boosts compared to the baselines and achieves state-of-the-art performance for ViT-Base and ViT-Large models in ImageNet-1K classification task. Moreover, GGeM outperforms the existing pooling strategies on image retrieval and multi-modal representation learning tasks, demonstrating the superiority of GGeM for a variety of tasks. GGeM is a simple algorithm in that only a few lines of code are necessary for implementation.
PDF
点此查看论文截图