Mennatullah Siam

Mennatullah Siam, Rezaul Karim, He Zhao et al.

Few-shot video segmentation is the task of delineating a specific novel class in a query video using few labelled support images. Typical approaches compare support and query features while limiting comparisons to a single feature layer and thereby ignore potentially valuable information. We present a meta-learned Multiscale Memory Comparator (MMC) for few-shot video segmentation that combines information across scales within a transformer decoder. Typical multiscale transformer decoders for segmentation tasks learn a compressed representation, their queries, through information exchange across scales. Unlike previous work, we instead preserve the detailed feature maps during across scale information exchange via a multiscale memory transformer decoding to reduce confusion between the background and novel class. Integral to the approach, we investigate multiple forms of information exchange across scales in different tasks and provide insights with empirical evidence on which to use in each task. The overall comparisons among query and support features benefit from both rich semantics and precise localization. We demonstrate our approach primarily on few-shot video object segmentation and an adapted version on the fully supervised counterpart. In all cases, our approach outperforms the baseline and yields state-of-the-art performance. Our code is publicly available at https://github.com/MSiam/MMC-MultiscaleMemory.

Matthew Kowal, Mennatullah Siam, Md Amirul Islam et al.

Deep spatiotemporal models are used in a variety of computer vision tasks, such as action recognition and video object segmentation. Currently, there is a limited understanding of what information is captured by these models in their intermediate representations. For example, while it has been observed that action recognition algorithms are heavily influenced by visual appearance in single static frames, there is no quantitative methodology for evaluating such static bias in the latent representation compared to bias toward dynamic information (e.g. motion). We tackle this challenge by proposing a novel approach for quantifying the static and dynamic biases of any spatiotemporal model. To show the efficacy of our approach, we analyse two widely studied tasks, action recognition and video object segmentation. Our key findings are threefold: (i) Most examined spatiotemporal models are biased toward static information; although, certain two-stream architectures with cross-connections show a better balance between the static and dynamic information captured. (ii) Some datasets that are commonly assumed to be biased toward dynamics are actually biased toward static information. (iii) Individual units (channels) in an architecture can be biased toward static, dynamic or a combination of the two.

Matthew Kowal, Mennatullah Siam, Md Amirul Islam et al.

There is limited understanding of the information captured by deep spatiotemporal models in their intermediate representations. For example, while evidence suggests that action recognition algorithms are heavily influenced by visual appearance in single frames, no quantitative methodology exists for evaluating such static bias in the latent representation compared to bias toward dynamics. We tackle this challenge by proposing an approach for quantifying the static and dynamic biases of any spatiotemporal model, and apply our approach to three tasks, action recognition, automatic video object segmentation (AVOS) and video instance segmentation (VIS). Our key findings are: (i) Most examined models are biased toward static information. (ii) Some datasets that are assumed to be biased toward dynamics are actually biased toward static information. (iii) Individual channels in an architecture can be biased toward static, dynamic or a combination of the two. (iv) Most models converge to their culminating biases in the first half of training. We then explore how these biases affect performance on dynamically biased datasets. For action recognition, we propose StaticDropout, a semantically guided dropout that debiases a model from static information toward dynamics. For AVOS, we design a better combination of fusion and cross connection layers compared with previous architectures.

Rezaul Karim, He Zhao, Richard P. Wildes et al.

In this paper, we present an end-to-end trainable unified multiscale encoder-decoder transformer that is focused on dense prediction tasks in video. The presented Multiscale Encoder-Decoder Video Transformer (MED-VT) uses multiscale representation throughout and employs an optional input beyond video (e.g., audio), when available, for multimodal processing (MED-VT++). Multiscale representation at both encoder and decoder yields three key benefits: (i) implicit extraction of spatiotemporal features at different levels of abstraction for capturing dynamics without reliance on input optical flow, (ii) temporal consistency at encoding and (iii) coarse-to-fine detection for high-level (e.g., object) semantics to guide precise localization at decoding. Moreover, we present a transductive learning scheme through many-to-many label propagation to provide temporally consistent video predictions. We showcase MED-VT/MED-VT++ on three unimodal video segmentation tasks (Automatic Video Object Segmentation (AVOS), actor-action segmentation and Video Semantic Segmentation (VSS)) as well as a multimodal segmentation task (Audio-Visual Segmentation (AVS)). Results show that the proposed architecture outperforms alternative state-of-the-art approaches on multiple benchmarks using only video (and optional audio) as input, without reliance on optical flow. Finally, to document details of the model's internal learned representations, we present a detailed interpretability study, encompassing both quantitative and qualitative analyses.

Mennatullah Siam, Konstantinos G. Derpanis, Richard P. Wildes

Few-shot video object segmentation (FS-VOS) aims at segmenting video frames using a few labelled examples of classes not seen during initial training. In this paper, we present a simple but effective temporal transductive inference (TTI) approach that leverages temporal consistency in the unlabelled video frames during few-shot inference. Key to our approach is the use of both global and local temporal constraints. The objective of the global constraint is to learn consistent linear classifiers for novel classes across the image sequence, whereas the local constraint enforces the proportion of foreground/background regions in each frame to be coherent across a local temporal window. These constraints act as spatiotemporal regularizers during the transductive inference to increase temporal coherence and reduce overfitting on the few-shot support set. Empirically, our model outperforms state-of-the-art meta-learning approaches in terms of mean intersection over union on YouTube-VIS by 2.8%. In addition, we introduce improved benchmarks that are exhaustively labelled (i.e. all object occurrences are labelled, unlike the currently available), and present a more realistic evaluation paradigm that targets data distribution shift between training and testing sets. Our empirical results and in-depth analysis confirm the added benefits of the proposed spatiotemporal regularizers to improve temporal coherence and overcome certain overfitting scenarios.

Clifford Broni-Bediako, Junshi Xia, Jian Song et al.

Learning with limited labelled data is a challenging problem in various applications, including remote sensing. Few-shot semantic segmentation is one approach that can encourage deep learning models to learn from few labelled examples for novel classes not seen during the training. The generalized few-shot segmentation setting has an additional challenge which encourages models not only to adapt to the novel classes but also to maintain strong performance on the training base classes. While previous datasets and benchmarks discussed the few-shot segmentation setting in remote sensing, we are the first to propose a generalized few-shot segmentation benchmark for remote sensing. The generalized setting is more realistic and challenging, which necessitates exploring it within the remote sensing context. We release the dataset augmenting OpenEarthMap with additional classes labelled for the generalized few-shot evaluation setting. The dataset is released during the OpenEarthMap land cover mapping generalized few-shot challenge in the L3D-IVU workshop in conjunction with CVPR 2024. In this work, we summarize the dataset and challenge details in addition to providing the benchmark results on the two phases of the challenge for the validation and test sets.

Hesham Ali, Idriss Tondji, Mennatullah Siam

AI-assisted nuclei segmentation in histopathological images is a crucial task in the diagnosis and treatment of cancer diseases. It decreases the time required to manually screen microscopic tissue images and can resolve the conflict between pathologists during diagnosis. Deep Learning has proven useful in such a task. However, lack of labeled data is a significant barrier for deep learning-based approaches. In this study, we propose a novel approach to nuclei segmentation that leverages the available labelled and unlabelled data. The proposed method combines the strengths of both transductive and inductive learning, which have been previously attempted separately, into a single framework. Inductive learning aims at approximating the general function and generalizing to unseen test data, while transductive learning has the potential of leveraging the unlabelled test data to improve the classification. To the best of our knowledge, this is the first study to propose such a hybrid approach for medical image segmentation. Moreover, we propose a novel two-stage transductive inference scheme. We evaluate our approach on MoNuSeg benchmark to demonstrate the efficacy and potential of our method.

Mennatullah Siam

Multiple works have emerged to push the boundaries on multi-modal large language models (MLLMs) towards pixel-level understanding. The current trend in pixel-level MLLMs is to train with pixel-level grounding supervision on large-scale labelled data with specialized decoders for the segmentation task. However, we show that such MLLMs when evaluated on recent challenging vision-centric benchmarks, exhibit a weak ability in visual question answering (VQA). Surprisingly, some of these methods even downgrade the grounding ability of MLLMs that were never trained with such pixel-level supervision. In this work, we propose two novel challenging benchmarks with paired evaluation for both VQA and grounding. We show that MLLMs without pixel-level grounding supervision can outperform the state of the art in such tasks. Our paired benchmarks and evaluation enable additional analysis on the reasons for failure with respect to VQA and/or grounding. Furthermore, we propose simple baselines to extract the grounding information that can be plugged into any MLLM, which we call PixFoundation. More importantly, we study the research question of "When does grounding emerge in MLLMs that are not trained with pixel-level grounding supervision?" We show that grounding can coincide with object parts, its location, appearance, context or state, where we show 27-45% of the examples in both benchmarks exhibit this phenomenon. Our code and datasets will be made publicly available and some are in the supplemental.

Mennatullah Siam

Multi-modal large language models (MLLMs) have shown impressive generalization across tasks using images and text modalities. While their extension to video has enabled tasks such as video question answering and video captioning, their pixel-level visual grounding abilities are less studied. In this work, we raise the pertinent question of whether motion is used in pixel-level visual grounding and whether video MLLMs can segment objects based on natural language expressions describing their motion patterns. We identify the shortcomings in the current benchmarks, where we show that a single frame can often suffice for capturing the motion referring expression without any temporal reasoning. To address this, we introduce four motion-centric probing techniques, particularly designed for the visual grounding task, to study video MLLMs' ability to identify true motion from a fake one and their ability to grasp the motion order. Consequently, we provide a motion-centric benchmark, MoCentric-Bench. It ensures that video MLLMs are evaluated towards leveraging the interaction between motion and language rather than being dominated by static appearance cues emphasized in existing visual grounding datasets. We further establish strong single-image baselines that are on par with or outperform prior methods. Finally, we explore simple motion-centric adaptation techniques that provide state-of-the-art performance on our MoCentric-Bench. Our motion-centric benchmark, evaluation and findings challenge future models to improve dense spatiotemporal grounding and pixel-level understanding within videos. Code and datasets will be made publicly available at https://github.com/MSiam/PixFoundation-2.0.git.

Mennatullah Siam, Alex Kendall, Martin Jagersand

Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects. Motivated by safety reasons, we address the video class agnostic segmentation task, which considers unknown objects outside the closed set of known classes in our training data. We propose a novel auxiliary contrastive loss to learn the segmentation of known classes and unknown objects. Unlike previous work in contrastive learning that samples the anchor, positive and negative examples on an image level, our contrastive learning method leverages pixel-wise semantic and temporal guidance. We conduct experiments on Cityscapes-VPS by withholding four classes from training and show an improvement gain for both known and unknown objects segmentation with the auxiliary contrastive loss. We further release a large-scale synthetic dataset for different autonomous driving scenarios that includes distinct and rare unknown objects. We conduct experiments on the full synthetic dataset and a reduced small-scale version, and show how contrastive learning is more effective in small scale datasets. Our proposed models, dataset, and code will be released at https://github.com/MSiam/video_class_agnostic_segmentation.

Mennatullah Siam, Boris Oreshkin, Martin Jagersand

Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We propose a novel adaptive masked proxies method that constructs the final segmentation layer weights from few labelled samples. It utilizes multi-resolution average pooling on base embeddings masked with the label to act as a positive proxy for the new class, while fusing it with the previously learned class signatures. Our method is evaluated on PASCAL-$5^i$ dataset and outperforms the state-of-the-art in the few-shot semantic segmentation. Unlike previous methods, our approach does not require a second branch to estimate parameters or prototypes, which enables it to be used with 2-stream motion and appearance based segmentation networks. We further propose a novel setup for evaluating continual learning of object segmentation which we name incremental PASCAL (iPASCAL) where our method outperforms the baseline method. Our code is publicly available at https://github.com/MSiam/AdaptiveMaskedProxies.

Mennatullah Siam, Mostafa Gamal, Moemen Abdel-Razek et al.

Semantic segmentation benefits robotics related applications especially autonomous driving. Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally efficient solutions. The few work conducted in this direction does not provide principled methods to evaluate the different design choices for segmentation. In this paper, we address this gap by presenting a real-time semantic segmentation benchmarking framework with a decoupled design for feature extraction and decoding methods. The framework is comprised of different network architectures for feature extraction such as VGG16, Resnet18, MobileNet, and ShuffleNet. It is also comprised of multiple meta-architectures for segmentation that define the decoding methodology. These include SkipNet, UNet, and Dilation Frontend. Experimental results are presented on the Cityscapes dataset for urban scenes. The modular design allows novel architectures to emerge, that lead to 143x GFLOPs reduction in comparison to SegNet. This benchmarking framework is publicly available at "https://github.com/MSiam/TFSegmentation".

Abhineet Singh, Mennatullah Siam, Martin Jagersand

This paper adapts a popular image quality measure called structural similarity for high precision registration based tracking while also introducing a simpler and faster variant of the same. Further, these are evaluated comprehensively against existing measures using a unified approach to study registration based trackers that decomposes them into three constituent sub modules - appearance model, state space model and search method. Several popular trackers in literature are broken down using this method so that their contributions - as of this paper - are shown to be limited to only one or two of these submodules. An open source tracking framework is made available that follows this decomposition closely through extensive use of generic programming. It is used to perform all experiments on four publicly available datasets so the results are easily reproducible. This framework provides a convenient interface to plug in a new method for any sub module and combine it with existing methods for the other two. It can also serve as a fast and flexible solution for practical tracking needs due to its highly efficient implementation.

Mir Rayat Imtiaz Hossain, Mennatullah Siam, Leonid Sigal et al.

The emergence of attention-based transformer models has led to their extensive use in various tasks, due to their superior generalization and transfer properties. Recent research has demonstrated that such models, when prompted appropriately, are excellent for few-shot inference. However, such techniques are under-explored for dense prediction tasks like semantic segmentation. In this work, we examine the effectiveness of prompting a transformer-decoder with learned visual prompts for the generalized few-shot segmentation (GFSS) task. Our goal is to achieve strong performance not only on novel categories with limited examples, but also to retain performance on base categories. We propose an approach to learn visual prompts with limited examples. These learned visual prompts are used to prompt a multiscale transformer decoder to facilitate accurate dense predictions. Additionally, we introduce a unidirectional causal attention mechanism between the novel prompts, learned with limited examples, and the base prompts, learned with abundant data. This mechanism enriches the novel prompts without deteriorating the base class performance. Overall, this form of prompting helps us achieve state-of-the-art performance for GFSS on two different benchmark datasets: COCO-$20^i$ and Pascal-$5^i$, without the need for test-time optimization (or transduction). Furthermore, test-time optimization leveraging unlabelled test data can be used to improve the prompts, which we refer to as transductive prompt tuning.

Raghav Goyal, Wan-Cyuan Fan, Mennatullah Siam et al.

Video Object Segmentation (VOS) has emerged as an increasingly important problem with availability of larger datasets and more complex and realistic settings, which involve long videos with global motion (e.g, in egocentric settings), depicting small objects undergoing both rigid and non-rigid (including state) deformations. While a number of recent approaches have been explored for this task, these data characteristics still present challenges. In this work we propose a novel, clip-based DETR-style encoder-decoder architecture, which focuses on systematically analyzing and addressing aforementioned challenges. Specifically, we propose a novel transformation-aware loss that focuses learning on portions of the video where an object undergoes significant deformations -- a form of "soft" hard examples mining. Further, we propose a multiplicative time-coded memory, beyond vanilla additive positional encoding, which helps propagate context across long videos. Finally, we incorporate these in our proposed holistic multi-scale video transformer for tracking via multi-scale memory matching and decoding to ensure sensitivity and accuracy for long videos and small objects. Our model enables on-line inference with long videos in a windowed fashion, by breaking the video into clips and propagating context among them. We illustrate that short clip length and longer memory with learned time-coding are important design choices for improved performance. Collectively, these technical contributions enable our model to achieve new state-of-the-art (SoTA) performance on two complex egocentric datasets -- VISOR and VOST, while achieving comparable to SoTA results on the conventional VOS benchmark, DAVIS'17. A series of detailed ablations validate our design choices as well as provide insights into the importance of parameter choices and their impact on performance.

Mir Rayat Imtiaz Hossain, Mennatullah Siam, Leonid Sigal et al.

Large-scale vision-language models (VLMs), trained on extensive datasets of image-text pairs, exhibit strong multimodal understanding capabilities by implicitly learning associations between textual descriptions and image regions. This emergent ability enables zero-shot object detection and segmentation, using techniques that rely on text-image attention maps, without necessarily training on abundant labeled segmentation datasets. However, performance of such methods depends heavily on prompt engineering and manually selected layers or head choices for the attention layers. In this work, we demonstrate that, rather than relying solely on textual prompts, providing a single visual example for each category and fine-tuning the text-to-image attention layers and embeddings significantly improves the performance. Additionally, we propose learning an ensemble through few-shot fine-tuning across multiple layers and/or prompts. An entropy-based ranking and selection mechanism for text-to-image attention layers is proposed to identify the top-performing layers without the need for segmentation labels. This eliminates the need for hyper-parameter selection of text-to-image attention layers, providing a more flexible and scalable solution for open-vocabulary segmentation. We show that this approach yields strong zero-shot performance, further enhanced through fine-tuning with a single visual example. Moreover, we demonstrate that our method and findings are general and can be applied across various vision-language models (VLMs).

Mai Gamal, Mohamed Rashad, Eman Ehab et al.

Extensive literature has drawn comparisons between recordings of biological neurons in the brain and deep neural networks. This comparative analysis aims to advance and interpret deep neural networks and enhance our understanding of biological neural systems. However, previous works did not consider the time aspect and how the encoding of video and dynamics in deep networks relate to the biological neural systems within a large-scale comparison. Towards this end, we propose the first large-scale study focused on comparing video understanding models with respect to the visual cortex recordings using video stimuli. The study encompasses more than two million regression fits, examining image vs. video understanding, convolutional vs. transformer-based and fully vs. self-supervised models. Additionally, we propose a novel neural encoding scheme to better encode biological neural systems. We provide key insights on how video understanding models predict visual cortex responses; showing video understanding better than image understanding models, convolutional models are better in the early-mid visual cortical regions than transformer based ones except for multiscale transformers, and that two-stream models are better than single stream. Furthermore, we propose a novel neural encoding scheme that is built on top of the best performing video understanding models, while incorporating inter-intra region connectivity across the visual cortex. Our neural encoding leverages the encoded dynamics from video stimuli, through utilizing two-stream networks and multiscale transformers, while taking connectivity priors into consideration. Our results show that merging both intra and inter-region connectivity priors increases the encoding performance over each one of them standalone or no connectivity priors. It also shows the necessity for encoding dynamics to fully benefit from such connectivity priors.

Leila Cheshmi, Mennatullah Siam

Ensuring safety in autonomous driving is a complex challenge requiring handling unknown objects and unforeseen driving scenarios. We develop multiscale video transformers capable of detecting unknown objects using only motion cues. Video semantic and panoptic segmentation often relies on known classes seen during training, overlooking novel categories. Recent visual grounding with large language models is computationally expensive, especially for pixel-level output. We propose an efficient video transformer trained end-to-end for class-agnostic segmentation without optical flow. Our method uses multi-stage multiscale query-memory decoding and a scale-specific random drop-token to ensure efficiency and accuracy, maintaining detailed spatiotemporal features with a shared, learnable memory module. Unlike conventional decoders that compress features, our memory-centric design preserves high-resolution information at multiple scales. We evaluate on DAVIS'16, KITTI, and Cityscapes. Our method consistently outperforms multiscale baselines while being efficient in GPU memory and run-time, demonstrating a promising direction for real-time, robust dense prediction in safety-critical robotics.

Abduljaleel Adejumo, Faegheh Yeganli, Clifford Broni-bediako et al.

Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision-language tasks but their remote sensing (RS) counterpart are relatively under explored. Unlike natural images, RS imagery presents unique challenges that current MLLMs struggle to handle, particularly in visual grounding and spatial reasoning. This study investigates the limitations of CLIP-based MLLMs in RS, highlighting their failure to differentiate visually distinct yet semantically similar RS images. To address this, we introduce a remote sensing multimodal visual patterns (RSMMVP) benchmark. It is designed to evaluate MLLMs in RS tasks by identifying the CLIP-blind pairs, where CLIP-based models incorrectly assign high similarity scores to visually distinct RS images. Through a visual question answering (VQA) evaluation, we analyze the performance of state-of-the-art MLLMs, revealing significant limitations in RS specific representation learning. The results provide valuable insights into the weaknesses of CLIP-based visual encoding and offer a foundation for future research to develop more effective MLLMs tailored for remote sensing applications.

Abdul-Hakeem Omotayo, Ashery Mbilinyi, Lukman Ismaila et al.

Despite significant efforts to democratize artificial intelligence (AI), computer vision which is a sub-field of AI, still lags in Africa. A significant factor to this, is the limited access to computing resources, datasets, and collaborations. As a result, Africa's contribution to top-tier publications in this field has only been 0.06% over the past decade. Towards improving the computer vision field and making it more accessible and inclusive, this study analyzes 63,000 Scopus-indexed computer vision publications from Africa. We utilize large language models to automatically parse their abstracts, to identify and categorize topics and datasets. This resulted in listing more than 100 African datasets. Our objective is to provide a comprehensive taxonomy of dataset categories to facilitate better understanding and utilization of these resources. We also analyze collaboration trends of researchers within and outside the continent. Additionally, we conduct a large-scale questionnaire among African computer vision researchers to identify the structural barriers they believe require urgent attention. In conclusion, our study offers a comprehensive overview of the current state of computer vision research in Africa, to empower marginalized communities to participate in the design and development of computer vision systems.

Abdul-Hakeem Omotayo, Mai Gamal, Eman Ehab et al.

Computer vision is a broad field of study that encompasses different tasks (e.g., object detection). Although computer vision is relevant to the African communities in various applications, yet computer vision research is under-explored in the continent and constructs only 0.06% of top-tier publications in the last ten years. In this paper, our goal is to have a better understanding of the computer vision research conducted in Africa and provide pointers on whether there is equity in research or not. We do this through an empirical analysis of the African computer vision publications that are Scopus indexed, where we collect around 63,000 publications over the period 2012-2022. We first study the opportunities available for African institutions to publish in top-tier computer vision venues. We show that African publishing trends in top-tier venues over the years do not exhibit consistent growth, unlike other continents such as North America or Asia. Moreover, we study all computer vision publications beyond top-tier venues in different African regions to find that mainly Northern and Southern Africa are publishing in computer vision with 68.5% and 15.9% of publications, resp. Nonetheless, we highlight that both Eastern and Western Africa are exhibiting a promising increase with the last two years closing the gap with Southern Africa. Additionally, we study the collaboration patterns in these publications to find that most of these exhibit international collaborations rather than African ones. We also show that most of these publications include an African author that is a key contributor as the first or last author. Finally, we present the most recurring keywords in computer vision publications per African region.

Mennatullah Siam, Alex Kendall, Martin Jagersand

Semantic segmentation approaches are typically trained on large-scale data with a closed finite set of known classes without considering unknown objects. In certain safety-critical robotics applications, especially autonomous driving, it is important to segment all objects, including those unknown at training time. We formalize the task of video class agnostic segmentation from monocular video sequences in autonomous driving to account for unknown objects. Video class agnostic segmentation can be formulated as an open-set or a motion segmentation problem. We discuss both formulations and provide datasets and benchmark different baseline approaches for both tracks. In the motion-segmentation track we benchmark real-time joint panoptic and motion instance segmentation, and evaluate the effect of ego-flow suppression. In the open-set segmentation track we evaluate baseline methods that combine appearance, and geometry to learn prototypes per semantic class. We then compare it to a model that uses an auxiliary contrastive loss to improve the discrimination between known and unknown objects. Datasets and models are publicly released at https://msiam.github.io/vca/.

Eslam Mohamed, Mahmoud Ewaisha, Mennatullah Siam et al.

Moving object segmentation is a crucial task for autonomous vehicles as it can be used to segment objects in a class agnostic manner based on their motion cues. It enables the detection of unseen objects during training (e.g., moose or a construction truck) based on their motion and independent of their appearance. Although pixel-wise motion segmentation has been studied in autonomous driving literature, it has been rarely addressed at the instance level, which would help separate connected segments of moving objects leading to better trajectory planning. As the main issue is the lack of large public datasets, we create a new InstanceMotSeg dataset comprising of 12.9K samples improving upon our KITTIMoSeg dataset. In addition to providing instance level annotations, we have added 4 additional classes which is crucial for studying class agnostic motion segmentation. We adapt YOLACT and implement a motion-based class agnostic instance segmentation model which would act as a baseline for the dataset. We also extend it to an efficient multi-task model which additionally provides semantic instance segmentation sharing the encoder. The model then learns separate prototype coefficients within the class agnostic and semantic heads providing two independent paths of object detection for redundant safety. To obtain real-time performance, we study different efficient encoders and obtain 39 fps on a Titan Xp GPU using MobileNetV2 with an improvement of 10% mAP relative to the baseline. Our model improves the previous state of the art motion segmentation method by 3.3%. The dataset and qualitative results video are shared in our website at https://sites.google.com/view/instancemotseg/.

Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin et al.

Significant progress has been made recently in developing few-shot object segmentation methods. Learning is shown to be successful in few-shot segmentation settings, using pixel-level, scribbles and bounding box supervision. This paper takes another approach, i.e., only requiring image-level label for few-shot object segmentation. We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embedding. Our model using image-level labels achieves 4.8% improvement over previously proposed image-level few-shot object segmentation. It also outperforms state-of-the-art methods that use weak bounding box supervision on PASCAL-5i. Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels. We further propose a novel setup, Temporal Object Segmentation for Few-shot Learning (TOSFL) for videos. TOSFL can be used on a variety of public video data such as Youtube-VOS, as demonstrated in both instance-level and category-level TOSFL experiments.

Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin et al.

Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks. Recent work has shown to perform on par with weaker levels of supervision in terms of scribbles and bounding boxes. However, there has been limited attention given to the problem of few-shot object segmentation with image-level supervision. We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embeddings. It enables our model to achieve 5.1% improvement over previously proposed image-level few-shot object segmentation. Our method compares relatively close to the state of the art methods that use strong supervision, while ours use the least possible supervision. We further propose a novel setup for few-shot weakly supervised video object segmentation(VOS) that relies on image-level labels for the first frame. The proposed setup uses weak annotation unlike semi-supervised VOS setting that utilizes strongly labelled segmentation masks. The setup evaluates the effectiveness of generalizing to novel classes in the VOS setting. The setup splits the VOS data into multiple folds with different categories per fold. It provides a potential setup to evaluate how few-shot object segmentation methods can benefit from additional object poses, or object interactions that is not available in static frames as in PASCAL-5i benchmark.

Mennatullah Siam, Chen Jiang, Steven Lu et al.

Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments, since the total number of objects and their variations can be intractable. Inspired by the children learning process, human robot interaction (HRI) can be utilized to teach robots about the world guided by humans similar to how children learn from a parent or a teacher. A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing manual segmentation labels. We propose a novel teacher-student learning paradigm to teach robots about their surrounding environment. A two-stream motion and appearance "teacher" network provides pseudo-labels to adapt an appearance "student" network. The student network is able to segment the newly learned objects in other scenes, whether they are static or in motion. We also introduce a carefully designed dataset that serves the proposed HRI setup, denoted as (I)nteractive (V)ideo (O)bject (S)egmentation. Our IVOS dataset contains teaching videos of different objects, and manipulation tasks. Unlike previous datasets, IVOS provides manipulation tasks sequences with segmentation annotation along with the waypoints for the robot trajectories. It also provides segmentation annotation for the different transformations such as translation, scale, planar rotation, and out-of-plane rotation. Our proposed adaptation method outperforms the state-of-the-art on DAVIS and FBMS with 6.8% and 1.2% in F-measure respectively. It improves over the baseline on IVOS dataset with 46.1% and 25.9% in mIoU.

Masood Dehghan, Zichen Zhang, Mennatullah Siam et al.

This work describes the development of a robotic system that acquires knowledge incrementally through human interaction where new tools and motions are taught on the fly. The robotic system developed was one of the five finalists in the KUKA Innovation Award competition and demonstrated during the Hanover Messe 2018 in Germany. The main contributions of the system are a) a novel incremental object learning module - a deep learning based localization and recognition system - that allows a human to teach new objects to the robot, b) an intuitive user interface for specifying 3D motion task associated with the new object, c) a hybrid force-vision control module for performing compliant motion on an unstructured surface. This paper describes the implementation and integration of the main modules of the system and summarizes the lessons learned from the competition.

Mostafa Gamal, Mennatullah Siam, Moemen Abdel-Razek

Real-time semantic segmentation is of significant importance for mobile and robotics related applications. We propose a computationally efficient segmentation network which we term as ShuffleSeg. The proposed architecture is based on grouped convolution and channel shuffling in its encoder for improving the performance. An ablation study of different decoding methods is compared including Skip architecture, UNet, and Dilation Frontend. Interesting insights on the speed and accuracy tradeoff is discussed. It is shown that skip architecture in the decoding method provides the best compromise for the goal of real-time performance, while it provides adequate accuracy by utilizing higher resolution feature maps for a more accurate segmentation. ShuffleSeg is evaluated on CityScapes and compared against the state of the art real-time segmentation networks. It achieves 2x GFLOPs reduction, while it provides on par mean intersection over union of 58.3% on CityScapes test set. ShuffleSeg runs at 15.7 frames per second on NVIDIA Jetson TX2, which makes it of great potential for real-time applications.

Mennatullah Siam, Heba Mahgoub, Mohamed Zahran et al.

We propose a novel multi-task learning system that combines appearance and motion cues for a better semantic reasoning of the environment. A unified architecture for joint vehicle detection and motion segmentation is introduced. In this architecture, a two-stream encoder is shared among both tasks. In order to evaluate our method in autonomous driving setting, KITTI annotated sequences with detection and odometry ground truth are used to automatically generate static/dynamic annotations on the vehicles. This dataset is called KITTI Moving Object Detection dataset (KITTI MOD). The dataset will be made publicly available to act as a benchmark for the motion detection task. Our experiments show that the proposed method outperforms state of the art methods that utilize motion cue only with 21.5% in mAP on KITTI MOD. Our method performs on par with the state of the art unsupervised methods on DAVIS benchmark for generic object segmentation. One of our interesting conclusions is that joint training of motion segmentation and vehicle detection benefits motion segmentation. Motion segmentation has relatively fewer data, unlike the detection task. However, the shared fusion encoder benefits from joint training to learn a generalized representation. The proposed method runs in 120 ms per frame, which beats the state of the art motion detection/segmentation in computational efficiency.

Mennatullah Siam, Sara Elkerdawy, Martin Jagersand et al.

Semantic segmentation was seen as a challenging computer vision problem few years ago. Due to recent advancements in deep learning, relatively accurate solutions are now possible for its use in automated driving. In this paper, the semantic segmentation problem is explored from the perspective of automated driving. Most of the current semantic segmentation algorithms are designed for generic images and do not incorporate prior structure and end goal for automated driving. First, the paper begins with a generic taxonomic survey of semantic segmentation algorithms and then discusses how it fits in the context of automated driving. Second, the particular challenges of deploying it into a safety system which needs high level of accuracy and robustness are listed. Third, different alternatives instead of using an independent semantic segmentation module are explored. Finally, an empirical evaluation of various semantic segmentation architectures was performed on CamVid dataset in terms of accuracy and speed. This paper is a preliminary shorter version of a more detailed survey which is work in progress.

Mennatullah Siam, Abhineet Singh, Camilo Perez et al.

This paper presents two visual trackers from the different paradigms of learning and registration based tracking and evaluates their application in image based visual servoing. They can track object motion with four degrees of freedom (DoF) which, as we will show here, is sufficient for many fine manipulation tasks. One of these trackers is a newly developed learning based tracker that relies on learning discriminative correlation filters while the other is a refinement of a recent 8 DoF RANSAC based tracker adapted with a new appearance model for tracking 4 DoF motion. Both trackers are shown to provide superior performance to several state of the art trackers on an existing dataset for manipulation tasks. Further, a new dataset with challenging sequences for fine manipulation tasks captured from robot mounted eye-in-hand (EIH) cameras is also presented. These sequences have a variety of challenges encountered during real tasks including jittery camera movement, motion blur, drastic scale changes and partial occlusions. Quantitative and qualitative results on these sequences are used to show that these two trackers are robust to failures while providing high precision that makes them suitable for such fine manipulation tasks.

Mennatullah Siam, Sepehr Valipour, Martin Jagersand et al.

Semantic segmentation has recently witnessed major progress, where fully convolutional neural networks have shown to perform well. However, most of the previous work focused on improving single image segmentation. To our knowledge, no prior work has made use of temporal video information in a recurrent network. In this paper, we introduce a novel approach to implicitly utilize temporal data in videos for online semantic segmentation. The method relies on a fully convolutional network that is embedded into a gated recurrent architecture. This design receives a sequence of consecutive video frames and outputs the segmentation of the last frame. Convolutional gated recurrent networks are used for the recurrent part to preserve spatial connectivities in the image. Our proposed method can be applied in both online and batch segmentation. This architecture is tested for both binary and semantic video segmentation tasks. Experiments are conducted on the recent benchmarks in SegTrack V2, Davis, CityScapes, and Synthia. Using recurrent fully convolutional networks improved the baseline network performance in all of our experiments. Namely, 5% and 3% improvement of F-measure in SegTrack2 and Davis respectively, 5.7% improvement in mean IoU in Synthia and 3.5% improvement in categorical mean IoU in CityScapes. The performance of the RFCN network depends on its baseline fully convolutional network. Thus RFCN architecture can be seen as a method to improve its baseline segmentation network by exploiting spatiotemporal information in videos.

Sepehr Valipour, Mennatullah Siam, Eleni Stroulia et al.

Parking management systems, and vacancy-indication services in particular, can play a valuable role in reducing traffic and energy waste in large cities. Visual detection methods represent a cost-effective option, since they can take advantage of hardware usually already available in many parking lots, namely cameras. However, visual detection methods can be fragile and not easily generalizable. In this paper, we present a robust detection algorithm based on deep convolutional neural networks. We implemented and tested our algorithm on a large baseline dataset, and also on a set of image feeds from actual cameras already installed in parking lots. We have developed a fully functional system, from server-side image analysis to front-end user interface, to demonstrate the practicality of our method.

Sepehr Valipour, Mennatullah Siam, Martin Jagersand et al.

Image segmentation is an important step in most visual tasks. While convolutional neural networks have shown to perform well on single image segmentation, to our knowledge, no study has been been done on leveraging recurrent gated architectures for video segmentation. Accordingly, we propose a novel method for online segmentation of video sequences that incorporates temporal data. The network is built from fully convolutional element and recurrent unit that works on a sliding window over the temporal data. We also introduce a novel convolutional gated recurrent unit that preserves the spatial information and reduces the parameters learned. Our method has the advantage that it can work in an online fashion instead of operating over the whole input batch of video frames. The network is tested on the change detection dataset, and proved to have 5.5\% improvement in F-measure over a plain fully convolutional network for per frame segmentation. It was also shown to have improvement of 1.4\% for the F-measure compared to our baseline network that we call FCN 12s.