2nd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation

• URL: http://arxiv.org/abs/2406.08192v1
• Date: Wed, 12 Jun 2024 13:21:33 GMT
• Title: 2nd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation
• Abstract summary: We use instance segmentation to generate extra pretraining data from the valid and test set of MOSE. The segmented instances are combined with objects extracted from COCO to augment the training data and enhance semantic representation of the baseline model. Our method ranked 2nd in the MOSE track of PVUW 2024, with a $mathcalJ$ of 0.8007, a $mathcalF$ of 0.8683 and a $mathcalJ$&$mathcalF$ of 0.8345.
• Score: 8.858448849921832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Complex video object segmentation serves as a fundamental task for a wide range of downstream applications such as video editing and automatic data annotation. Here we present the 2nd place solution in the MOSE track of PVUW 2024. To mitigate problems caused by tiny objects, similar objects and fast movements in MOSE. We use instance segmentation to generate extra pretraining data from the valid and test set of MOSE. The segmented instances are combined with objects extracted from COCO to augment the training data and enhance semantic representation of the baseline model. Besides, motion blur is added during training to increase robustness against image blur induced by motion. Finally, we apply test time augmentation (TTA) and memory strategy to the inference stage. Our method ranked 2nd in the MOSE track of PVUW 2024, with a $\mathcal{J}$ of 0.8007, a $\mathcal{F}$ of 0.8683 and a $\mathcal{J}$\&$\mathcal{F}$ of 0.8345.

Related papers

• MASSeg : 2nd Technical Report for 4th PVUW MOSE Track [4.988774092444048]
  We propose an improved model named MASSeg for complex video object segmentation, and construct an enhanced dataset, MOSE+. During training, we incorporate a combination of inter-frame consistent and inconsistent data augmentation strategies to improve robustness and generalization. MASSeg achieves a J score of 0.8250, F score of 0.9007, and a J&F score of 0.8628 on the MOSE test set.
  arXiv  Detail & Related papers  (2025-04-14T14:15:46Z)
• Segment Any Motion in Videos [80.72424676419755]
  We propose a novel approach for moving object segmentation that combines long-range trajectory motion cues with DINO-based semantic features. Our model employs Spatio-Temporal Trajectory Attention and Motion-Semantic Decoupled Embedding to prioritize motion while integrating semantic support.
  arXiv  Detail & Related papers  (2025-03-28T09:34:11Z)
• 1st Place Solution for MOSE Track in CVPR 2024 PVUW Workshop: Complex Video Object Segmentation [72.54357831350762]
  We propose a semantic embedding video object segmentation model and use the salient features of objects as query representations. We trained our model on a large-scale video object segmentation dataset. Our model achieves first place (textbf84.45%) in the test set of Complex Video Object Challenge.
  arXiv  Detail & Related papers  (2024-06-07T03:13:46Z)
• 3rd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation [63.199793919573295]
  Video Object (VOS) is a vital task in computer vision, focusing on distinguishing foreground objects from the background across video frames. Our work draws inspiration from the Cutie model, and we investigate the effects of object memory, the total number of memory frames, and input resolution on segmentation performance.
  arXiv  Detail & Related papers  (2024-06-06T00:56:25Z)
• Coarse-to-Fine Amodal Segmentation with Shape Prior [52.38348188589834]
  Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. We propose a novel approach called Coarse-to-Fine: C2F-Seg, that addresses this problem by progressively modeling the amodal segmentation.
  arXiv  Detail & Related papers  (2023-08-31T15:56:29Z)
• DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition [62.95223898214866]
  We explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field. With a pyramid architecture, we construct a Multi-Scale Dilated Transformer (DilateFormer) by stacking MSDA blocks at low-level stages and global multi-head self-attention blocks at high-level stages. Our experiment results show that our DilateFormer achieves state-of-the-art performance on various vision tasks.
  arXiv  Detail & Related papers  (2023-02-03T14:59:31Z)
• Pose for Everything: Towards Category-Agnostic Pose Estimation [93.07415325374761]
  Category-Agnostic Pose Estimation (CAPE) aims to create a pose estimation model capable of detecting the pose of any class of object given only a few samples with keypoint definition. A transformer-based Keypoint Interaction Module (KIM) is proposed to capture both the interactions among different keypoints and the relationship between the support and query images. We also introduce Multi-category Pose (MP-100) dataset, which is a 2D pose dataset of 100 object categories containing over 20K instances and is well-designed for developing CAPE algorithms.
  arXiv  Detail & Related papers  (2022-07-21T09:40:54Z)
• Segmenting Moving Objects via an Object-Centric Layered Representation [100.26138772664811]
  We introduce an object-centric segmentation model with a depth-ordered layer representation. We introduce a scalable pipeline for generating synthetic training data with multiple objects. We evaluate the model on standard video segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-07-05T17:59:43Z)
• Multi-Modal and Multi-Factor Branching Time Active Inference [2.513785998932353]
  Two versions of branching time active inference (BTAI) based on Monte-Carlo tree search have been developed. However, those two versions of BTAI still suffer from an exponential complexity class w.r.t the number of observed and latent variables being modelled. In this paper, we resolve this limitation by allowing the modelling of several observations, each of them having its own likelihood mapping. The inference algorithm then exploits the factorisation of the likelihood and transition mappings to accelerate the computation of the posterior.
  arXiv  Detail & Related papers  (2022-06-24T22:07:21Z)
• Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency [28.352140544936198]
  Weakly supervised instance segmentation reduces the cost of annotations required to train models. We show that these issues can be better addressed by training with weakly labeled videos instead of images. We are the first to explore the use of these video signals to tackle weakly supervised instance segmentation.
  arXiv  Detail & Related papers  (2021-03-23T23:20:46Z)
• Monocular Instance Motion Segmentation for Autonomous Driving: KITTI InstanceMotSeg Dataset and Multi-task Baseline [5.000331633798637]
  Moving object segmentation is a crucial task for autonomous vehicles as it can be used to segment objects in a class agnostic manner. Although pixel-wise motion segmentation has been studied in autonomous driving literature, it has been rarely addressed at the instance level. We create a new InstanceMotSeg dataset comprising of 12.9K samples improving upon our KITTIMoSeg dataset.
  arXiv  Detail & Related papers  (2020-08-16T21:47:09Z)
• Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos [23.153335327822685]
  We learn a motion-centric representation of surgical video demonstrations by grouping them into action segments/sub-goals/options. We present Motion2Vec, an algorithm that learns a deep embedding feature space from video observations. We demonstrate the use of this representation to imitate surgical suturing motions from publicly available videos of the JIGSAWS dataset.
  arXiv  Detail & Related papers  (2020-05-31T15:46:01Z)

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.