Semi-supervised Video Object Segmentation Research Articles

Scalable Video Object Segmentation With Identification Mechanism.

This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS). Previous VOS methods decode features with a single positive object, limiting the learning of multi-object representation as they must match and segment each target separately under multi-object scenarios. Additionally, earlier techniques catered to specific application objectives and lacked the flexibility to fulfill different speed-accuracy requirements. To address these problems, we present two innovative approaches, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST). In pursuing effective multi-object modeling, AOT introduces the IDentification (ID) mechanism to allocate each object a unique identity. This approach enables the network to model the associations among all objects simultaneously, thus facilitating the tracking and segmentation of objects in a single network pass. To address the challenge of inflexible deployment, AOST further integrates scalable long short-term transformers that incorporate scalable supervision and layer-wise ID-based attention. This enables online architecture scalability in VOS for the first time and overcomes ID embeddings' representation limitations. Given the absence of a benchmark for VOS involving densely multi-object annotations, we propose a challenging Video Object Segmentation in the Wild (VOSW) benchmark to validate our approaches. We evaluated various AOT and AOST variants using extensive experiments across VOSW and five commonly used VOS benchmarks, including YouTube-VOS 2018 & 2019 Val, DAVIS-2017 Val & Test, and DAVIS-2016. Our approaches surpass the state-of-the-art competitors and display exceptional efficiency and scalability consistently across all six benchmarks. Moreover, we notably achieved the 1st position in the 3 rd Large-scale Video Object Segmentation Challenge.

Lester: Rotoscope Animation through Video Object Segmentation and Tracking

This article introduces Lester, a novel method to automatically synthesize retro-style 2D animations from videos. The method approaches the challenge mainly as an object segmentation and tracking problem. Video frames are processed with the Segment Anything Model (SAM) and the resulting masks are tracked through subsequent frames with DeAOT, a method of hierarchical propagation for semi-supervised video object segmentation. The geometry of the masks’ contours is simplified with the Douglas–Peucker algorithm. Finally, facial traits, pixelation and a basic rim light effect can be optionally added. The results show that the method exhibits an excellent temporal consistency and can correctly process videos with different poses and appearances, dynamic shots, partial shots and diverse backgrounds. The proposed method provides a more simple and deterministic approach than diffusion models based video-to-video translation pipelines, which suffer from temporal consistency problems and do not cope well with pixelated and schematic outputs. The method is also more feasible than techniques based on 3D human pose estimation, which require custom handcrafted 3D models and are very limited with respect to the type of scenes they can process.

Structural Transformer with Region Strip Attention for Video Object Segmentation

Memory-based methods in semi-supervised video object segmentation (VOS) achieve competitive performance by performing feature similarity between the current frame and memory frames. However, this operation involves two challenges: 1) instances of occlusion caused by interaction, and 2) interference from similar objects or clutters in the background. In this work, we propose a Structural Transformer with Region Strip Attention (STRSA) approach to address these challenges. Specifically, we build a Structural Transformer (ST) architecture to decompose the feature similarity between the long-term memory frames and the current frame into two aspects: a time–space part and an object significance part. This allows us to investigate the spatio-temporal relationship of pixels and capture the salient features of the objects. Therefore, the differences between pixels and the specificity of objects are fully exploited. In addition, we leverage the object location information from the long-term memory masks and the strip pooling to design a Region Strip Attention (RSA) module, which boosts the attention for the foreground regions and suppresses the background clutters. Extensive experiments on DAVIS, YouTube-VOS, and MOSE benchmarks prove that our method achieves satisfactory results and outperforms the retrained baseline model.

G-TRACE: Grouped temporal recalibration for video object segmentation

In Semi-supervised Video Object Segmentation (SVOS), there is a critical emphasis on enhancing the memory and readout mechanisms for frame matching, especially in relation to temporal dynamics. Current methods predominantly use 2D CNNs for encoding video frames, which unfortunately neglects the crucial aspect of addressing temporal variations in individual frames and their associated masks during the encoding process. One potential solution would be to implement temporal models such as 3D CNNs instead of 2D CNNs, but this significantly increases computational requirements, making it impractical for real-world SVOS applications. In this paper, we introduce the Grouped Temporal Recalibration with Attention for Convolutional Encoders (G-TRACE), a novel plug-and-play module that is compatible with various existing SVOS frameworks. G-TRACE uses hierarchical memory-centric attention and integrates effortlessly with 2D CNNs, offering a novel approach to temporal modeling that operates orthogonally to traditional frame matching methods. Extensive evaluations on four widely-used benchmarks demonstrate that our method consistently delivers significant performance improvements over various baseline models.

Mitigating Distractor Challenges in Video Object Segmentation through Shape and Motion Cues

The purpose of semi-supervised video object segmentation (VOS) is to predict and generate object masks in subsequent video frames after being provided with the initial frame’s object mask. Currently, mainstream methods leverage historical frame information for enhancing the network’s performance. However, this approach faces the following issues: (1) They often overlook important shape information, leading to decreased accuracy in segmenting object-edge areas. (2) They often use pixel-level motion estimation to guide the matching for addressing distractor objects. However, this brings heavy computation costs and struggle against occlusion or fast/blurry motion. For the first problem, this paper introduces an object shape extraction module that exploits both the high-level and low-level features to obtain object shape information, by which the shape information can be used to further refine the predicted masks. For the second problem, this paper introduces a novel object-level motion prediction module, in which it stores the representative motion features during the training stage, and predicts the object motion by retrieving them during the inference stage. We evaluate our method on benchmark datasets compared with recent state-of-the-art methods, and the results demonstrate the effectiveness of the proposed method.

STAVOS: A Medaka Larval Cardiac Video Segmentation Method Based on Deep Learning

Medaka (Oryzias latipes), as a crucial model organism in biomedical research, holds significant importance in fields such as cardiovascular diseases. Currently, the analysis of the medaka ventricle relies primarily on visual observation under a microscope, involving labor-intensive manual operations and visual assessments that are cumbersome and inefficient for biologists. Despite attempts by some scholars to employ machine learning methods, limited datasets and challenges posed by the blurred edges of the medaka ventricle have constrained research to relatively simple tasks such as ventricle localization and heart rate statistics, lacking precise segmentation of the medaka ventricle edges. To address these issues, we initially constructed a video object segmentation dataset comprising over 7000 microscopic images of medaka ventricles. Subsequently, we proposed a semi-supervised video object segmentation model named STAVOS, incorporating a spatial-temporal attention mechanism. Additionally, we developed an automated system capable of calculating various parameters and visualizing results for a medaka ventricle using the provided video. The experimental results demonstrate that STAVOS has successfully achieved precise segmentation of medaka ventricle contours. In comparison to the conventional U-Net model, where a mean accuracy improvement of 0.392 was achieved, our model demonstrates significant progress. Furthermore, when compared to the state-of-the-art Tackling Background Distraction (TBD) model, there is an additional enhancement of 0.038.

Region Aware Video Object Segmentation With Deep Motion Modeling.

Current semi-supervised video object segmentation (VOS) methods often employ the entire features of one frame to predict object masks and update memory. This introduces significant redundant computations. To reduce redundancy, we introduce a Region Aware Video Object Segmentation (RAVOS) approach, which predicts regions of interest (ROIs) for efficient object segmentation and memory storage. RAVOS includes a fast object motion tracker to predict object ROIs in the next frame. For efficient segmentation, object features are extracted based on the ROIs, and an object decoder is designed for object-level segmentation. For efficient memory storage, we propose motion path memory to filter out redundant context by memorizing the features within the motion path of objects. In addition to RAVOS, we also propose a large-scale occluded VOS dataset, dubbed OVOS, to benchmark the performance of VOS models under occlusions. Evaluation on DAVIS and YouTube-VOS benchmarks and our new OVOS dataset show that our method achieves state-of-the-art performance with significantly faster inference time, e.g., 86.1 J & F at 42 FPS on DAVIS and 84.4 J & F at 23 FPS on YouTube-VOS. Project page: ravos.netlify.app.

MobileSAM-Track: Lightweight One-Shot Tracking and Segmentation of Small Objects on Edge Devices

Tracking and segmenting small targets in remote sensing videos on edge devices carries significant engineering implications. However, many semi-supervised video object segmentation (S-VOS) methods heavily rely on extensive video random-access memory (VRAM) resources, making deployment on edge devices challenging. Our goal is to develop an edge-deployable S-VOS method that can achieve high-precision tracking and segmentation by selecting a bounding box for the target object. First, a tracker is introduced to pinpoint the position of the tracked object in different frames, thereby eliminating the need to save the results of the split as other S-VOS methods do, thus avoiding an increase in VRAM usage. Second, we use two key lightweight components, correlation filters (CFs) and the Mobile Segment Anything Model (MobileSAM), to ensure the inference speed of our model. Third, a mask diffusion module is proposed that improves the accuracy and robustness of segmentation without increasing VRAM usage. We use our self-built dataset containing airplanes and vehicles to evaluate our method. The results show that on the GTX 1080 Ti, our model achieves a J&F score of 66.4% under the condition that the VRAM usage is less than 500 MB, while maintaining a processing speed of 12 frames per second (FPS). The model we propose exhibits good performance in tracking and segmenting small targets on edge devices, providing a solution for fields such as aircraft monitoring and vehicle tracking that require executing S-VOS tasks on edge devices.

Spatial constraint for efficient semi-supervised video object segmentation

Semi-supervised video object segmentation is the process of tracking and segmenting objects in a video sequence based on annotated masks for one or more frames. Recently, memory-based methods have attracted a significant amount of attention due to their strong performance. Having too much redundant information stored in memory, however, makes such methods inefficient and inaccurate. Moreover, a global matching strategy is usually used for memory reading, so these methods are susceptible to interference from semantically similar objects and are prone to incorrect segmentation. We propose a spatial constraint network to overcome these problems. In particular, we introduce a time-varying sensor and a dynamic feature memory to adaptively store pixel information to facilitate the modeling of the target object, which greatly reduces information redundancy in the memory without missing critical information. Furthermore, we propose an efficient memory reader that is less computationally intensive and has a smaller footprint. More importantly, we introduce a spatial constraint module to learn spatial consistency to obtain more precise segmentation; the target and distractors can be identified by the learned spatial response. The experimental results indicate that our method is competitive with state-of-the-art methods on several benchmark datasets. Our method also achieves an approximately 30 FPS inference speed, which is close to the requirement for real-time systems.

Semi-supervised video object segmentation via an edge attention gated graph convolutional network

Video object segmentation (VOS) exhibits heavy occlusions, large deformation, and severe motion blur. While many remarkable convolutional neural networks are devoted to the VOS task, they often mis-identify background noise as the target or output coarse object boundaries, due to the failure of mining detail information and high-order correlations of pixels within the whole video. In this work, we propose an edge attention gated graph convolutional network (GCN) for VOS. The seed point initialization and graph construction stages construct a spatio-temporal graph of the video by exploring the spatial intra-frame correlation and the temporal inter-frame correlation of superpixels. The node classification stage identifies foreground superpixels by using an edge attention gated GCN which mines higher-order correlations between superpixels and propagates features among different nodes. The segmentation optimization stage optimizes the classification of foreground superpixels and reduces segmentation errors by using a global appearance model which captures the long-term stable feature of objects. In summary, the key contribution of our framework is twofold: (a) the spatio-temporal graph representation can propagate the seed points of the first frame to subsequent frames and facilitate our framework for the semi-supervised VOS task; (b) the edge attention gated GCN can learn the importance of each node with respect to both the neighboring nodes and the whole task with small number of layers. Experiments on Davis 2016 and Davis 2017 datasets show that our framework achieves the excellent performance with only small training samples (45 video sequences).

Complementary Coarse-to-Fine Matching for Video Object Segmentation

Semi-supervised Video Object Segmentation (VOS) needs to establish pixel-level correspondences between a video frame and preceding segmented frames to leverage their segmentation clues. Most works rely on features at a single scale to establish those correspondences, e.g., perform dense matching with Convolutional Neural Network (CNN) features from a deep layer. Differently, this work explores complementary features at different scales to pursue more robust feature matching. A coarse feature from a deep layer is first adopted to get coarse pixel-level correspondences. We hence evaluate the quality of those correspondences, and select pixels with low-quality correspondences for fine-scale feature matching. Segmentation clues of previous frames are propagated by both coarse and fine-scale correspondences, which are fused with appearance features for object segmentation. Compared with previous works, this coarse-to-fine matching scheme is more robust to distractions by similar objects and better preserves object details. The sparse fine-scale matching also ensures a fast inference speed. On popular VOS datasets including DAVIS and YouTube-VOS, the proposed method shows promising performance compared with recent works.

Learning to Learn Better for Video Object Segmentation

Recently, the joint learning framework (JOINT) integrates matching based transductive reasoning and online inductive learning to achieve accurate and robust semi-supervised video object segmentation (SVOS). However, using the mask embedding as the label to guide the generation of target features in the two branches may result in inadequate target representation and degrade the performance. Besides, how to reasonably fuse the target features in the two different branches rather than simply adding them together to avoid the adverse effect of one dominant branch has not been investigated. In this paper, we propose a novel framework that emphasizes Learning to Learn Better (LLB) target features for SVOS, termed LLB, where we design the discriminative label generation module (DLGM) and the adaptive fusion module to address these issues. Technically, the DLGM takes the background-filtered frame instead of the target mask as input and adopts a lightweight encoder to generate the target features, which serves as the label of the online few-shot learner and the value of the decoder in the transformer to guide the two branches to learn more discriminative target representation. The adaptive fusion module maintains a learnable gate for each branch, which reweighs the element-wise feature representation and allows an adaptive amount of target information in each branch flowing to the fused target feature, thus preventing one branch from being dominant and making the target feature more robust to distractor. Extensive experiments on public benchmarks show that our proposed LLB method achieves state-of-the-art performance.

Fast Real-Time Video Object Segmentation with a Tangled Memory Network

In this article, we present a fast real-time tangled memory network that segments the objects effectively and efficiently for semi-supervised video object segmentation (VOS). We propose a tangled reference encoder and a memory bank organization mechanism based on a state estimator to fully utilize the mask features and alleviate memory overhead and computational burden brought by the unlimited memory bank used in many memory-based methods. First, the tangled memory network exploits the mask features that uncover abundant object information like edges and contours but are not fully explored in existing methods. Specifically, a tangled two-stream reference encoder is designed to extract and fuse the features from both RGB frames and the predicted masks. Second, to indicate the quality of the predicted mask and feedback the online prediction state for organizing the memory bank, we devise a target state estimator to learn the IoU score between the predicted mask and ground truth. Moreover, to accelerate the forward process and avoid memory overflow, we use a memory bank of fixed size to store historical features by designing a new efficient memory bank organization mechanism based on the mask state score provided by the state estimator. We conduct comprehensive experiments on the public benchmarks DAVIS and YouTube-VOS, demonstrating that our method obtains competitive results while running at high speed (66 FPS on the DAVIS16-val set).

MUNet: Motion uncertainty-aware semi-supervised video object segmentation

The task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to retrieve relevant information from all available sources, where the past frames with object masks form an external memory and the current frame as the query is segmented using the mask information in the memory. However, when forming the memory and performing matching, these methods only exploit the appearance information while ignoring the motion information. In this paper, we advocate for the return of the motion information and propose a motion uncertainty-aware framework (MUNet) for semi-supervised VOS. First, we propose an implicit method to learn the spatial correspondences between neighboring frames, building upon a correlation cost volume. To handle the challenging cases of occlusion and textureless regions during constructing dense correspondences, we incorporate the uncertainty in dense matching and achieve motion uncertainty-aware feature representation. Second, we introduce a motion-aware spatial attention module to effectively fuse the motion features with the semantic features. Comprehensive experiments on challenging benchmarks show that using a small amount of data and combining it with powerful motion information can bring a significant performance boost. We achieve 76.5%J&F only using DAVIS17 for training22This result is initialized by the Mask-RCNN-ResNet50 weights pre-trained on COCO dataset. By initialization from ResNet50 pre-trained on ImageNet dataset, we can achieve 75.0%J&F, which is still the SOTA performance., which significantly outperforms the SOTA methods under the low-data protocol. The code and supplementary materials will be available at https://npucvr.github.io/MUNet.

Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels.

Semi-supervised video object segmentation (VOS) is to predict the segment of a target object in a video when a ground truth segmentation mask for the target is given in the first frame. Recently, space-time memory networks (STM) have received significant attention as a promising approach for semi-supervised VOS. However, an important point has been overlooked in applying STM to VOS: The solution (=STM) is non-local, but the problem (=VOS) is predominantly local. To solve this mismatch between STM and VOS, we propose new VOS networks called kernelized memory network (KMN) and KMN with multiple kernels (KMN M). Our networks conduct not only Query-to-Memory matching but also Memory-to-Query matching. In Memory-to-Query matching, a kernel is employed to reduce the degree of non-localness of the STM. In addition, we present a Hide-and-Seek strategy in pre-training to handle occlusions effectively. The proposed networks surpass the state-of-the-art results on standard benchmarks by a significant margin (+4% in JM on DAVIS 2017 test-dev set). The runtimes of our proposed KMN and KMN M on DAVIS 2016 validation set are 0.12 and 0.13 seconds per frame, respectively, and the two networks have similar computation times to STM.

Global video object segmentation with spatial constraint module

We present a lightweight and efficient semi-supervised video object segmentation network based on the space-time memory framework. To some extent, our method solves the two difficulties encountered in traditional video object segmentation: one is that the single frame calculation time is too long, and the other is that the current frame’s segmentation should use more information from past frames. The algorithm uses a global context (GC) module to achieve high-performance, real-time segmentation. The GC module can effectively integrate multi-frame image information without increased memory and can process each frame in real time. Moreover, the prediction mask of the previous frame is helpful for the segmentation of the current frame, so we input it into a spatial constraint module (SCM), which constrains the areas of segments in the current frame. The SCM effectively alleviates mismatching of similar targets yet consumes few additional resources. We added a refinement module to the decoder to improve boundary segmentation. Our model achieves state-of-the-art results on various datasets, scoring 80.1% on YouTube-VOS 2018 and a {cal J}{rm{& }}{cal F} score of 78.0% on DAVIS 2017, while taking 0.05 s per frame on the DAVIS 2016 validation dataset.

Prototypical Matching Networks for Video Object Segmentation.

Semi-supervised video object segmentation is the task of segmenting the target in sequential frames given the ground truth mask in the first frame. The modern approaches usually utilize such a mask as pixel-level supervision and typically exploit pixel-to-pixel matching between the reference frame and current frame. However, the matching at pixel level, which overlooks the high-level information beyond local areas, often suffers from confusion caused by similar local appearances. In this paper, we present Prototypical Matching Networks (PMNet) - a novel architecture that integrates prototypes into matching-based video objection segmentation frameworks as high-level supervision. Specifically, PMNet first divides the foreground and background areas into several parts according to the similarity to the global prototypes. The part-level prototypes and instance-level prototypes are generated by encapsulating the semantic information of identical parts and identical instances, respectively. To model the correlation between prototypes, the prototype representations are propagated to each other by reasoning on a graph structure. Then, PMNet stores both the pixel-level features and prototypes in the memory bank as the target cues. Three affinities, i.e., pixel-to-pixel affinity, prototype-to-pixel affinity, and prototype-to-prototype affinity, are derived to measure the similarity between the query frame and the features in the memory bank. The features aggregated from the memory bank using these affinities provide powerful discrimination from both the pixel-level and prototype-level perspectives. Extensive experiments conducted on four benchmarks demonstrate superior results than the state-of-the-art video object segmentation techniques.

Semi-Supervised Video Object Segmentation via Learning Object-Aware Global-Local Correspondence

In semi-supervised video object segmentation (VOS) task, temporal coherent object-level cues play a key role yet are hard to accurately model. To this end, this paper presents an object-aware global-local correspondence architecture, which enables to extract the inter-frame temporal coherent object-level features for accurate VOS. Specifically, we first generate a set of object masks by the ground-truth segmentation, and then we squeeze the current frame representation inside the object masks into a set of global object embeddings. Second, we compute the similarity between each embedding and the feature map, producing an object-aware weight for each pixel. The object-aware feature at each pixel is then constructed by summing the object embeddings weighted by their corresponding object-aware weights, which is able to capture rich object category information. Third, to establish the accurate correspondences between the inter-frame temporal coherent cues, we further design a novel global-local correspondence module to refine the temporal feature representations. Finally, we augment the object-aware features with the global-local aligned information to produce a strong spatio-temporal representation, which is essential to a more reliable pixel-wise segmentation prediction. Extensive evaluations are conducted on three popular VOS benchmarks containing Youtube-VOS, Davis2017 and Davis2016, demonstrating that the proposed method achieves favourable performance compared to the state-of-the-arts.

Coherence-aware context aggregator for fast video object segmentation

Semi-supervised video object segmentation (VOS) is a highly challenging problem that has attracted much research attention in recent years. Temporal context plays an important role in VOS by providing object clues from the past frames. However, most of the prevailing methods directly use the predicted temporal results to guide the segmentation of the current frame, while ignoring the coherence of temporal context, which may be misleading and degrade the performance. In this paper, we propose a novel model named Coherence-aware Context Aggregator (CCA) for VOS, which consists of three modules. First, a coherence-aware module (CAM) is proposed to evaluate the coherence of the predicted result of the current frame and then fuses the coherent features to update the temporal context. CAM can determine whether the prediction is accurate, thus guiding the update of the temporal context and avoiding the introduction of erroneous information. Second, we devise a spatio-temporal context aggregation (STCA) module to aggregate the temporal context with the spatial feature of the current frame to learn a robust and discriminative target representation in the decoder part. Third, we design a refinement module to refine the coarse feature generated from the STCA module for more precise segmentation. Additionally, CCA uses a cropping strategy and takes small-size images as input, thus making it computationally efficient and achieving a real-time running speed. Extensive experiments on four challenging benchmarks show that CCA achieves a better trade-off between efficiency and accuracy compared to state-of-the-art methods. The code will be public.

Video Object Segmentation using Point-based Memory Network

Recent years have witnessed the prevalence of memory-based methods for Semi-supervised Video Object Segmentation (SVOS) which utilise past frames efficiently for label propagation. When conducting feature matching, fine-grained multi-scale feature matching has typically been performed using all query points, which inevitably results in redundant computations and thus makes the fusion of multi-scale results ineffective. In this paper, we develop a new Point-based Memory Network, termed as PMNet, to perform fine-grained feature matching on hard samples only, assuming that easy samples can already obtain satisfactory matching results without the need for complicated multi-scale feature matching. Our approach first generates an uncertainty map from the initial decoding outputs. Next, the fine-grained features at uncertain locations are sampled to match the memory features on the same scale. Finally, the matching results are further decoded to provide a refined output. The point-based scheme works with the coarsest feature matching in a complementary and efficient manner. Furthermore, we propose an approach to adaptively perform global or regional matching based on the motion history of memory points, making our method more robust against ambiguous backgrounds. Experimental results on several benchmark datasets demonstrate the superiority of our proposed method over state-of-the-art methods.