Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation

• URL: http://arxiv.org/abs/2404.13505v1
• Date: Sun, 21 Apr 2024 02:21:30 GMT
• Title: Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation
• Authors: Gensheng Pei, Yazhou Yao, Jianbo Jiao, Wenguan Wang, Liqiang Nie, Jinhui Tang,
• Abstract summary: We present HVC, a framework for self-supervised video object segmentation. HVC extracts pseudo-dynamic signals from static images, enabling an efficient and scalable VOS model. We propose a hybrid visual correspondence loss to learn joint static and dynamic consistency representations.
• Score: 126.12940972028012
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conventional video object segmentation (VOS) methods usually necessitate a substantial volume of pixel-level annotated video data for fully supervised learning. In this paper, we present HVC, a \textbf{h}ybrid static-dynamic \textbf{v}isual \textbf{c}orrespondence framework for self-supervised VOS. HVC extracts pseudo-dynamic signals from static images, enabling an efficient and scalable VOS model. Our approach utilizes a minimalist fully-convolutional architecture to capture static-dynamic visual correspondence in image-cropped views. To achieve this objective, we present a unified self-supervised approach to learn visual representations of static-dynamic feature similarity. Firstly, we establish static correspondence by utilizing a priori coordinate information between cropped views to guide the formation of consistent static feature representations. Subsequently, we devise a concise convolutional layer to capture the forward / backward pseudo-dynamic signals between two views, serving as cues for dynamic representations. Finally, we propose a hybrid visual correspondence loss to learn joint static and dynamic consistency representations. Our approach, without bells and whistles, necessitates only one training session using static image data, significantly reducing memory consumption ($\sim$16GB) and training time ($\sim$\textbf{2h}). Moreover, HVC achieves state-of-the-art performance in several self-supervised VOS benchmarks and additional video label propagation tasks.

Related papers

• UniLearn: Enhancing Dynamic Facial Expression Recognition through Unified Pre-Training and Fine-Tuning on Images and Videos [83.48170683672427]
  UniLearn is a unified learning paradigm that integrates static facial expression recognition data to enhance DFER task. UniLearn consistently state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65%, 58.44%, and 76.68%, respectively.
  arXiv  Detail & Related papers  (2024-09-10T01:57:57Z)
• Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective [10.938290904843939]
  We propose "Bi-level Optimization of Learning Dynamic with Decoupling and Intervention" (BOLD-DI) to capture both static and dynamic semantics in a decoupled manner. Our method can be seamlessly integrated into the existing v-CL methods and experimental results highlight the significant improvements.
  arXiv  Detail & Related papers  (2024-07-19T06:53:54Z)
• Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videos [67.12603318660689]
  We propose a novel Hierarchical Visual- and Semantic-Aware Reasoning Network (HVSARN) HVSARN enables both visual- and semantic-aware query reasoning from object-level to frame-level. Experiments on three datasets demonstrate that our HVSARN achieves a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-03-02T08:00:22Z)
• DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments [6.5121327691369615]
  We present DytanVO, the first supervised learning-based VO method that deals with dynamic environments. Our method achieves an average improvement of 27.7% in ATE over state-of-the-art VO solutions in real-world dynamic environments.
  arXiv  Detail & Related papers  (2022-09-17T23:56:03Z)
• STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding [68.96574451918458]
  We propose a framework named STVG, which models visual-linguistic dependencies with a static branch and a dynamic branch. Both the static and dynamic branches are designed as cross-modal transformers. Our proposed method achieved 39.6% vIoU and won the first place in the HC-STVG of the Person in Context Challenge.
  arXiv  Detail & Related papers  (2022-07-06T15:48:58Z)
• PreViTS: Contrastive Pretraining with Video Tracking Supervision [53.73237606312024]
  PreViTS is an unsupervised SSL framework for selecting clips containing the same object. PreViTS spatially constrains the frame regions to learn from and trains the model to locate meaningful objects. We train a momentum contrastive (MoCo) encoder on VGG-Sound and Kinetics-400 datasets with PreViTS.
  arXiv  Detail & Related papers  (2021-12-01T19:49:57Z)
• Multi-modal Visual Place Recognition in Dynamics-Invariant Perception Space [23.43468556831308]
  This letter explores the use of multi-modal fusion of semantic and visual modalities to improve place recognition in dynamic environments. We achieve this by first designing a novel deep learning architecture to generate the static semantic segmentation. We then innovatively leverage the spatial-pyramid-matching model to encode the static semantic segmentation into feature vectors. In parallel, the static image is encoded using the popular Bag-of-words model.
  arXiv  Detail & Related papers  (2021-05-17T13:14:52Z)
• Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAM [6.693607456009373]
  We present a data-driven approach to obtain the static image of a scene, eliminating dynamic objects that might have been present at the time of traversing the scene with a camera. We introduce an end-to-end deep learning framework to turn images of an urban environment into realistic static frames suitable for localization and mapping.
  arXiv  Detail & Related papers  (2020-10-15T10:31:12Z)
• DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping [72.84991726271024]
  We describe an unsupervised method to detect and segment portions of images of live scenes that are seen moving as a coherent whole. Our method first partitions the motion field by minimizing the mutual information between segments. It uses the segments to learn object models that can be used for detection in a static image.
  arXiv  Detail & Related papers  (2020-08-16T22:05:13Z)

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.