ABSTRACT
Spatial-temporal structural details of targets in video (e.g. varying edges, textures over time) are essential to accurate Unsupervised Video Object Segmentation (UVOS). The vanilla multi-head self-attention in the Transformer-based UVOS methods usually concentrates on learning the general low-frequency information (e.g. illumination, color), while neglecting the high-frequency texture details, leading to unsatisfying segmentation results. To address this issue, this paper presents a Temporally efficient Gabor Transformer (TGFormer) for UVOS. The TGFormer jointly models the spatial dependencies and temporal coherence intra- and inter-frames, which can fully capture the rich structural details for accurate UVOS. Concretely, we first propose an effective learnable Gabor filtering Transformer to mine the structural texture details of the object for accurate UVOS. Then, to adaptively store the redundant neighboring historical information, we present an efficient dynamic neighboring frame selection module to automatically choose the useful temporal information, which simultaneously relieves the blurry frame and reduces the computation burden. Finally, we make the UVOS model be a fully Transformer architecture, meanwhile aggregating the information from space, Gabor and time domains, yielding a strong representation with rich structure details. Extensive experiments on five mainstream UVOS benchmarks (DAVIS2016, FBMS, DAVSOD, ViSal, and MCL) demonstrate the superiority of the presented solution to sate-of-the-art methods.
Supplemental Material
- Yael Adini, Yael Moses, and Shimon Ullman. 1997. Face recognition: The problem of compensating for changes in illumination direction. TPAMI (1997).Google Scholar
- Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Luvc ić, and Cordelia Schmid. 2021. Vivit: A video vision transformer. In ICCV.Google Scholar
- Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML.Google Scholar
- Adam Botach, Evgenii Zheltonozhskii, and Chaim Baskin. 2022. End-to-end referring video object segmentation with multimodal transformers. In CVPR.Google Scholar
- Yi-Wen Chen, Xiaojie Jin, Xiaohui Shen, and Ming-Hsuan Yang. 2022. Video Salient Object Detection via Contrastive Features and Attention Modules. In WACV.Google Scholar
- Deng-Ping Fan, Wenguan Wang, Ming-Ming Cheng, and Jianbing Shen. 2019. Shifting more attention to video salient object detection. In CVPR.Google Scholar
- Jiaqing Fan, Tiankang Su, Kaihua Zhang, and Qingshan Liu. 2022. Bidirectionally Learning Dense Spatio-temporal Feature Propagation Network for Unsupervised Video Object Segmentation. In ACMMM.Google Scholar
- Yuchao Gu, Lijuan Wang, Ziqin Wang, Yun Liu, Ming-Ming Cheng, and Shao-Ping Lu. 2020. Pyramid constrained self-attention network for fast video salient object detection. In AAAI.Google Scholar
- John Guibas, Morteza Mardani, Zongyi Li, Andrew Tao, Anima Anandkumar, and Bryan Catanzaro. 2022. Adaptive fourier neural operators: Efficient token mixers for transformers. In ICLR.Google Scholar
- Yuan-Ting Hu, Jia-Bin Huang, and Alexander G Schwing. 2018. Unsupervised video object segmentation using motion saliency-guided spatio-temporal propagation. In ECCV.Google Scholar
- Suyog Dutt Jain, Bo Xiong, and Kristen Grauman. 2017. Fusionseg: Learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In CVPR.Google Scholar
- Ge-Peng Ji, Keren Fu, Zhe Wu, Deng-Ping Fan, Jianbing Shen, and Ling Shao. 2021. Full-duplex strategy for video object segmentation. In ICCV.Google Scholar
- Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 2012. 3D convolutional neural networks for human action recognition. TPAMI (2012).Google Scholar
- Liming Jiang, Bo Dai, Wayne Wu, and Chen Change Loy. 2021. Focal frequency loss for image reconstruction and synthesis. In ICCV.Google Scholar
- Hansang Kim, Youngbae Kim, Jae-Young Sim, and Chang-Su Kim. 2015. Spatiotemporal saliency detection for video sequences based on random walk with restart. TIP (2015).Google Scholar
- Youngjo Lee, Hongje Seong, and Euntai Kim. 2022. Iteratively selecting an easy reference frame makes unsupervised video object segmentation easier. In AAAI.Google Scholar
- Shuai Li, Wanqing Li, Chris Cook, Ce Zhu, and Yanbo Gao. 2018a. Independently recurrent neural network (indrnn): Building a longer and deeper rnn. In CVPR.Google Scholar
- Siyang Li, Bryan Seybold, Alexey Vorobyov, Alireza Fathi, Qin Huang, and C-C Jay Kuo. 2018b. Instance embedding transfer to unsupervised video object segmentation. In CVPR.Google Scholar
- Chengjun Liu and Harry Wechsler. 2002. Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. TIP (2002).Google Scholar
- Daizong Liu, Dongdong Yu, Changhu Wang, and Pan Zhou. 2021. F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation. In AAAI.Google Scholar
- Yong Liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, and Yujiu Yang. 2022. Learning Quality-aware Dynamic Memory for Video Object Segmentation. In ECCV.Google Scholar
- Xiankai Lu, Wenguan Wang, Martin Danelljan, Tianfei Zhou, Jianbing Shen, and Luc Van Gool. 2020a. Video object segmentation with episodic graph memory networks. In ECCV.Google Scholar
- Xiankai Lu, Wenguan Wang, Chao Ma, Jianbing Shen, Ling Shao, and Fatih Porikli. 2019. See more, know more: Unsupervised video object segmentation with co-attention siamese networks. In CVPR.Google Scholar
- Xiankai Lu, Wenguan Wang, Jianbing Shen, Yu-Wing Tai, David J Crandall, and Steven CH Hoi. 2020b. Learning video object segmentation from unlabeled videos. In CVPR.Google Scholar
- Sachin Mehta and Mohammad Rastegari. 2022. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. In ICLR.Google Scholar
- Peter Ochs, Jitendra Malik, and Thomas Brox. 2013. Segmentation of moving objects by long term video analysis. TPAMI (2013).Google Scholar
- Youwei Pang, Xiaoqi Zhao, Lihe Zhang, and Huchuan Lu. 2020. Multi-scale interactive network for salient object detection. In CVPR.Google Scholar
- Namuk Park and Songkuk Kim. 2022. How Do Vision Transformers Work?. In ICLR.Google Scholar
- Gensheng Pei, Yazhou Yao, Guo-Sen Xie, Fumin Shen, Zhenmin Tang, and Jinhui Tang. 2022. Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation. In ECCV.Google Scholar
- Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams, Luc Van Gool, Markus Gross, and Alexander Sorkine-Hornung. 2016. A benchmark dataset and evaluation methodology for video object segmentation. In CVPR.Google Scholar
- Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, and Jie Zhou. 2021. Global filter networks for image classification. In NeurIPS.Google Scholar
- Sucheng Ren, Chu Han, Xin Yang, Guoqiang Han, and Shengfeng He. 2020. Tenet: Triple excitation network for video salient object detection. In ECCV.Google Scholar
- Sucheng Ren, Wenxi Liu, Yongtuo Liu, Haoxin Chen, Guoqiang Han, and Shengfeng He. 2021. Reciprocal transformations for unsupervised video object segmentation. In CVPR.Google Scholar
- Christian Schmidt, Ali Athar, Sabarinath Mahadevan, and Bastian Leibe. 2022. D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos. In WACV.Google Scholar
- Yuki Tatsunami and Masato Taki. 2022. Sequencer: Deep LSTM for Image Classification. In NeurIPS.Google Scholar
- Wenguan Wang, Xiankai Lu, Jianbing Shen, David J Crandall, and Ling Shao. 2019a. Zero-shot video object segmentation via attentive graph neural networks. In ICCV.Google Scholar
- Wenguan Wang, Jianbing Shen, and Ling Shao. 2015. Consistent video saliency using local gradient flow optimization and global refinement. TIP (2015).Google Scholar
- Wenguan Wang, Hongmei Song, Shuyang Zhao, Jianbing Shen, Sanyuan Zhao, Steven CH Hoi, and Haibin Ling. 2019b. Learning unsupervised video object segmentation through visual attention. In CVPR.Google Scholar
- Jun Wei, Shuhui Wang, and Qingming Huang. 2020. F3Net: fusion, feedback and focus for salient object detection. In AAAI.Google Scholar
- Jiannan Wu, Yi Jiang, Peize Sun, Zehuan Yuan, and Ping Luo. 2022. Language as Queries for Referring Video Object Segmentation. In CVPR.Google Scholar
- Jiangtao Xie, Fei Long, Jiaming Lv, Qilong Wang, and Peihua Li. 2022. Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification. In CVPR.Google Scholar
- Ning Xu, Linjie Yang, Yuchen Fan, Jianchao Yang, Dingcheng Yue, Yuchen Liang, Brian Price, Scott Cohen, and Thomas Huang. 2018. Youtube-vos: Sequence-to-sequence video object segmentation. In ECCV.Google Scholar
- Qinwei Xu, Ruipeng Zhang, Ya Zhang, Yanfeng Wang, and Qi Tian. 2021. A fourier-based framework for domain generalization. In CVPR.Google Scholar
- Shu Yang, Lu Zhang, Jinqing Qi, Huchuan Lu, Shuo Wang, and Xiaoxing Zhang. 2021. Learning Motion-Appearance Co-Attention for Zero-Shot Video Object Segmentation. In ICCV.Google Scholar
- Zhao Yang, Qiang Wang, Luca Bertinetto, Weiming Hu, Song Bai, and Philip HS Torr. 2019. Anchor diffusion for unsupervised video object segmentation. In ICCV.Google Scholar
- Hongxu Yin, Arash Vahdat, Jose M Alvarez, Arun Mallya, Jan Kautz, and Pavlo Molchanov. 2022. A-ViT: Adaptive Tokens for Efficient Vision Transformer. In CVPR.Google Scholar
- Bingyao Yu, Wanhua Li, Xiu Li, Jiwen Lu, and Jie Zhou. 2021. Frequency-aware spatiotemporal transformers for video inpainting detection. In ICCV.Google Scholar
- Kaihua Zhang, Zicheng Zhao, Dong Liu, Qingshan Liu, and Bo Liu. 2021b. Deep Transport Network for Unsupervised Video Object Segmentation. In ICCV.Google Scholar
- Miao Zhang, Jie Liu, Yifei Wang, Yongri Piao, Shunyu Yao, Wei Ji, Jingjing Li, Huchuan Lu, and Zhongxuan Luo. 2021a. Dynamic context-sensitive filtering network for video salient object detection. In ICCV.Google Scholar
- Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, and Lei Zhang. 2020. Suppress and balance: A simple gated network for salient object detection. In ECCV.Google Scholar
- Mingmin Zhen, Shiwei Li, Lei Zhou, Jiaxiang Shang, Haoan Feng, Tian Fang, and Long Quan. 2020. Learning discriminative feature with crf for unsupervised video object segmentation. In ECCV.Google Scholar
- Tianfei Zhou, Jianwu Li, Xueyi Li, and Ling Shao. 2021. Target-aware object discovery and association for unsupervised video multi-object segmentation. In CVPR.Google Scholar
- Tianfei Zhou, Fatih Porikli, David J Crandall, Luc Van Gool, and Wenguan Wang. 2022. A survey on deep learning technique for video segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 6 (2022), 7099--7122.Google ScholarDigital Library
- Tianfei Zhou, Shunzhou Wang, Yi Zhou, Yazhou Yao, Jianwu Li, and Ling Shao. 2020. Motion-attentive transition for zero-shot video object segmentation. In AAAI.Google Scholar
Index Terms
- Temporally Efficient Gabor Transformer for Unsupervised Video Object Segmentation
Recommendations
Gabor-Filtering-Based Completed Local Binary Patterns for Land-Use Scene Classification
BIGMM '15: Proceedings of the 2015 IEEE International Conference on Multimedia Big DataRemote sensing land-use scene classification has a wide range of applications including forestry, urban-growth analysis, and weather forecasting. This paper presents an effective image representation method, Gabor-filtering-based completed local binary ...
MEViT: Motion Enhanced Video Transformer for Video Classification
MultiMedia ModelingAbstractDue to the advantages in extracting the long-range dependencies, self-attention based transformers are widely used to model the spatio-temporal features for video classification, which achieves competitive performance compared to 3D CNNs. To ...
Unsupervised Segmentation of Color-Texture Regions in Images and Video
A new method for unsupervised segmentation of color-texture regions in images and video is presented. This method, which we refer to as JSEG, consists of two independent steps: color quantization and spatial segmentation. In the first step, colors in ...
Comments