SIGMA:Sinkhorn-Guided Masked Video Modeling

• URL: http://arxiv.org/abs/2407.15447v1
• Date: Mon, 22 Jul 2024 08:04:09 GMT
• Title: SIGMA:Sinkhorn-Guided Masked Video Modeling
• Authors: Mohammadreza Salehi, Michael Dorkenwald, Fida Mohammad Thoker, Efstratios Gavves, Cees G. M. Snoek, Yuki M. Asano,
• Abstract summary: Sinkhorn-guided Masked Video Modelling ( SIGMA) is a novel video pretraining method. We distribute features of space-time tubes evenly across a limited number of learnable clusters. Experimental results on ten datasets validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations.
• Score: 69.31715194419091
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising scalability, yet fall short in capturing higher-level semantics due to reconstructing predefined low-level targets such as pixels. To tackle this, we present Sinkhorn-guided Masked Video Modelling (SIGMA), a novel video pretraining method that jointly learns the video model in addition to a target feature space using a projection network. However, this simple modification means that the regular L2 reconstruction loss will lead to trivial solutions as both networks are jointly optimized. As a solution, we distribute features of space-time tubes evenly across a limited number of learnable clusters. By posing this as an optimal transport problem, we enforce high entropy in the generated features across the batch, infusing semantic and temporal meaning into the feature space. The resulting cluster assignments are used as targets for a symmetric prediction task where the video model predicts cluster assignment of the projection network and vice versa. Experimental results on ten datasets across three benchmarks validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations improving upon state-of-the-art methods. Our project website with code is available at: https://quva-lab.github.io/SIGMA.

Related papers

• TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale [59.01246141215051]
  We analyze the factor that leads to degradation from the perspective of language supervision. We propose a tunable-free pre-training strategy to retain the generalization ability of the text encoder. We produce a series of models, dubbed TVTSv2, with up to one billion parameters.
  arXiv  Detail & Related papers  (2023-05-23T15:44:56Z)
• RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving [80.14669385741202]
  Vision transformers (ViTs) have achieved state-of-the-art results in many image-based benchmarks. ViTs are notoriously hard to train and require a lot of training data to learn powerful representations. We show that our method, called RangeViT, outperforms existing projection-based methods on nuScenes and Semantic KITTI.
  arXiv  Detail & Related papers  (2023-01-24T18:50:48Z)
• Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling [28.530765643908083]
  We decouple spatial-temporal modeling and integrate an image- and a video-language to learn fine-grained visual understanding. We propose a novel pre-training objective, Temporal Referring Modeling, which requires the model to identify temporal positions of events in video sequences. Our model outperforms previous work pre-trained on orders of magnitude larger datasets.
  arXiv  Detail & Related papers  (2022-10-08T07:03:31Z)
• Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning [44.412145665354736]
  We introduce a novel contrastive action representation learning framework to learn frame-wise action representations. Inspired by the recent progress of self-supervised learning, we present a novel sequence contrastive loss (SCL) applied on two correlated views. Our approach also shows outstanding performance on video alignment and fine-grained frame retrieval tasks.
  arXiv  Detail & Related papers  (2022-03-28T17:59:54Z)
• ViViT: A Video Vision Transformer [75.74690759089529]
  We present pure-transformer based models for video classification. Our model extracts-temporal tokens from the input video, which are then encoded by a series of transformer layers. We show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets.
  arXiv  Detail & Related papers  (2021-03-29T15:27:17Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)
• Hybrid-S2S: Video Object Segmentation with Recurrent Networks and Correspondence Matching [3.9053553775979086]
  One-shot Video Object(VOS) is the task of tracking an object of interest within a video sequence. We study an RNN-based architecture and address some of these issues by proposing a hybrid sequence-to-sequence architecture named HS2S. Our experiments show that augmenting the RNN with correspondence matching is a highly effective solution to reduce the drift problem.
  arXiv  Detail & Related papers  (2020-10-10T19:00:43Z)
• Unsupervised Learning Consensus Model for Dynamic Texture Videos Segmentation [12.462608802359936]
  We present an effective unsupervised learning consensus model for the segmentation of dynamic texture (ULCM) In the proposed model, the set of values of the requantized local binary patterns (LBP) histogram around the pixel to be classified are used as features. Experiments conducted on the challenging SynthDB dataset show that ULCM is significantly faster, easier to code, simple and has limited parameters.
  arXiv  Detail & Related papers  (2020-06-29T16:40:59Z)
• Unsupervised Learning of Video Representations via Dense Trajectory Clustering [86.45054867170795]
  This paper addresses the task of unsupervised learning of representations for action recognition in videos. We first propose to adapt two top performing objectives in this class - instance recognition and local aggregation. We observe promising performance, but qualitative analysis shows that the learned representations fail to capture motion patterns.
  arXiv  Detail & Related papers  (2020-06-28T22:23:03Z)

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.