FODVid: Flow-guided Object Discovery in Videos
Not on the map. Why?
Abstract (arXiv)
Segmentation of objects in a video is challenging due to the nuances such as motion blurring, parallax, occlusions, changes in illumination, etc. Instead of addressing these nuances separately, we focus on building a generalizable solution that avoids overfitting to the individual intricacies. Such a solution would also help us save enormous resources involved in human annotation of video corpora. To solve Video Object Segmentation (VOS) in an unsupervised setting, we propose a new pipeline (FODVid) based on the idea of guiding segmentation outputs using flow-guided graph-cut and temporal consistency. Basically, we design a segmentation model incorporating intra-frame appearance and flow similarities, and inter-frame temporal continuation of the objects under consideration. We perform an extensive experimental analysis of our straightforward methodology on the standard DAVIS16 video benchmark. Though simple, our approach produces results comparable (within a range of ~2 mIoU) to the existing top approaches in unsupervised VOS. The simplicity and effectiveness of our technique opens up new avenues for research in the video domain.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 10 Jul 2023.
Builds on
28 of 43 references.
References · 28
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
- 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
- 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
- 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
- 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
- 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
- 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
- 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
16 more
- 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
- 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
- 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
- 2018On Regularized Losses for Weakly-supervised CNN Segmentationcited by 121
- 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
- 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
- 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
- 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
- 2019Unsupervised Moving Object Detection via Contextual Information Separationcited by 72
- 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
- 2022Deformable Sprites for Unsupervised Video Decompositioncited by 61
- 2021The Emergence of Objectness: Learning Zero-Shot Segmentation from Videoscited by 45
- 2022Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motioncited by 42
- 2022EM-driven unsupervised learning for efficient motion segmentationcited by 33
- 2015Decoupled Deep Neural Network for Semi-supervised Semantic Segmentationcited by 23
- 2022A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentationcited by 15
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.