Video Instance Segmentation by Instance Flow Assembly

نویسندگان

چکیده

Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their superiority into video domain. This because usually deal with features or images cropped from detected bounding boxes without alignment, failing to capture pixel-level temporal consistency. We embrace observation that bottom-up dealing box-free could offer accurate spacial correlations across frames, which can be fully utilized for pixel level tracking. first propose our framework equipped context fusion module better encode inter-frame correlations. Intra-frame cues semantic localization are simultaneously extracted reconstructed by corresponding decoders after shared backbone. For efficient robust tracking among instances, we introduce an instance-level correspondence adjacent represented center-to-center flow, termed as instance assemble messy dense correspondences. Experiments demonstrate proposed method outperforms state-of-the-art online (taking image-level input) on Youtube-VIS dataset [46].

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

MaskRNN: Instance Level Video Object Segmentation

Instance level video object segmentation is an important technique for video editing and compression. To capture the temporal coherence, in this paper, we develop MaskRNN, a recurrent neural net approach which fuses in each frame the output of two deep nets for each object instance — a binary segmentation net providing a mask and a localization net providing a bounding box. Due to the recurrent...

متن کامل

Shape-aware Instance Segmentation

We address the problem of instance-level semantic segmentation, which aims at jointly detecting, segmenting and classifying every individual object in an image. In this context, existing methods typically propose candidate objects, usually as bounding boxes, and directly predict a binary mask within each such proposal. As a consequence, they cannot recover from errors in the object candidate ge...

متن کامل

Recurrent Instance Segmentation

Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other, thus missing opportunities for joint learning. Here we propose a new instance segmentation paradigm consisting in an end-to-end method that learns how to se...

متن کامل

Amodal Instance Segmentation

We consider the problem of amodal instance segmentation, the objective of which is to predict the region encompassing both visible and occluded parts of each object. Thus far, the lack of publicly available amodal segmentation annotations has stymied the development of amodal segmentation methods. In this paper, we sidestep this issue by relying solely on standard modal instance segmentation an...

متن کامل

Instance Embedding Transfer to Unsupervised Video Object Segmentation

We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables identifying all pixels belonging to the same object. Though trained on static images, the instance embeddings are stable over consecutive video frames, which a...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Transactions on Multimedia

سال: 2022

ISSN: ['1520-9210', '1941-0077']

DOI: https://doi.org/10.1109/tmm.2022.3222643