Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection

• URL: http://arxiv.org/abs/2505.08561v1
• Date: Tue, 13 May 2025 13:35:41 GMT
• Title: Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection
• Authors: Ayush K. Rai, Kyle Min, Tarun Krishna, Feiyan Hu, Alan F. Smeaton, Noel E. O'Connor,
• Abstract summary: We introduce a novel and generalizable Trajectory-Aware Token Sampler (TATS)<n>TATS models the motion dynamics of tokens and can be seamlessly integrated into the masked autoencoder framework.<n>We show that our model allows aggressive masking without compromising performance on the downstream task of action recognition.
• Score: 12.421172561756473
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in such approaches lies in selecting an appropriate masking strategy. Previous studies have explored predefined masking techniques, including random and tube-based masking, as well as approaches that leverage key motion priors, optical flow and semantic cues from externally pre-trained models. In this work, we introduce a novel and generalizable Trajectory-Aware Adaptive Token Sampler (TATS), which models the motion dynamics of tokens and can be seamlessly integrated into the masked autoencoder (MAE) framework to select motion-centric tokens in videos. Additionally, we propose a unified training strategy that enables joint optimization of both MAE and TATS from scratch using Proximal Policy Optimization (PPO). We show that our model allows for aggressive masking without compromising performance on the downstream task of action recognition while also ensuring that the pre-training remains memory efficient. Extensive experiments of the proposed approach across four benchmarks, including Something-Something v2, Kinetics-400, UCF101, and HMDB51, demonstrate the effectiveness, transferability, generalization, and efficiency of our work compared to other state-of-the-art methods.

Related papers

• Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning [116.75939193785143]
  Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. In 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant.
  arXiv  Detail & Related papers  (2024-07-08T12:28:56Z)
• Emerging Property of Masked Token for Effective Pre-training [15.846621577804791]
  Masked Image Modeling (MIM) has been instrumental in driving recent breakthroughs in computer vision. MIM's overall efficiency is occasionally hampered by the lengthy duration of the pre-training phase. We propose a novel approach termed masked token optimization (MTO), specifically designed to improve model efficiency through weight recalibration and the enhancement of the key property of masked tokens.
  arXiv  Detail & Related papers  (2024-04-12T08:46:53Z)
• Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training [33.39585710223628]
  Saliency-Based Adaptive Masking improves pre-training performance of MIM approaches by prioritizing token salience. We show that our method significantly improves over the state-of-the-art in mask-based pre-training on the ImageNet-1K dataset.
  arXiv  Detail & Related papers  (2024-04-12T08:38:51Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• Boosting Adversarial Transferability with Learnable Patch-wise Masks [16.46210182214551]
  Adversarial examples have attracted widespread attention in security-critical applications because of their transferability across different models. In this paper, we argue that the model-specific discriminative regions are a key factor causing overfitting to the source model, and thus reducing the transferability to the target model. To accurately localize these regions, we present a learnable approach to automatically optimize the mask.
  arXiv  Detail & Related papers  (2023-06-28T05:32:22Z)
• Masked Autoencoding for Scalable and Generalizable Decision Making [93.84855114717062]
  MaskDP is a simple and scalable self-supervised pretraining method for reinforcement learning and behavioral cloning. We find that a MaskDP model gains the capability of zero-shot transfer to new BC tasks, such as single and multiple goal reaching.
  arXiv  Detail & Related papers  (2022-11-23T07:04:41Z)
• EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens [57.354304637367555]
  We present EVEREST, a surprisingly efficient MVA approach for video representation learning. It finds tokens containing rich motion features and discards uninformative ones during both pre-training and fine-tuning. Our method significantly reduces the computation and memory requirements of MVA.
  arXiv  Detail & Related papers  (2022-11-19T09:57:01Z)
• Exploring Target Representations for Masked Autoencoders [78.57196600585462]
  We show that a careful choice of the target representation is unnecessary for learning good representations. We propose a multi-stage masked distillation pipeline and use a randomly model as the teacher. A proposed method to perform masked knowledge distillation with bootstrapped teachers (dBOT) outperforms previous self-supervised methods by nontrivial margins.
  arXiv  Detail & Related papers  (2022-09-08T16:55:19Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models [54.569004548170824]
  We show that careful masking strategies can bridge the knowledge gap of masked language models. We propose an effective training strategy by adversarially masking out those tokens which are harder to adversarial by the underlying.
  arXiv  Detail & Related papers  (2020-10-05T01:49:47Z)
• Train No Evil: Selective Masking for Task-Guided Pre-Training [97.03615486457065]
  We propose a three-stage framework by adding a task-guided pre-training stage with selective masking between general pre-training and fine-tuning. We show that our method can achieve comparable or even better performance with less than 50% of cost.
  arXiv  Detail & Related papers  (2020-04-21T03:14:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.