Mennatullah Siam

Mennatullah Siam

Auto-generated profile, based on publicly available information

Mennatullah Siam

Computer Science, University of British Columbia, Vancouver, Canada

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 July 2021
Verified
Conference Paper
Open access
EMEslam Mohamed
Eslam Mohamed
MEMahmoud Ewaisha
Mahmoud Ewaisha
MSMennatullah Siam
Mennatullah Siam
HRHazem Rashed
Hazem Rashed
Senthil YogamaniSenthil Yogamani
Senthil Yogamani
AEAhmad El-Sallab
Ahmad El-Sallab
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.

1 November 2024 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
CBClifford Broni-Bediako
Clifford Broni-Bediako
Junshi XiaJunshi Xia
Junshi Xia
JSJian Song
Jian Song
HCHongruixuan Chen
Hongruixuan Chen
MSMennatullah Siam
Mennatullah Siam
Naoto YokoyaNaoto Yokoya
Naoto Yokoya
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.

6 March 2025 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
MSMennatullah Siam
Mennatullah Siam

17 September 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
MKMatthew Kowal
Matthew Kowal
MSMennatullah Siam
Mennatullah Siam
AIAmirul Islam
Amirul Islam
NBNeil D. B. Bruce
Neil D. B. Bruce
RWRichard P. Wildes
Richard P. Wildes
KDKonstantinos G. Derpanis
Konstantinos G. Derpanis
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 jointly encode a combination static and dynamic information. (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.


16 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
MSMennatullah Siam
Mennatullah Siam
KDKonstantinos G. Derpanis
Konstantinos G. Derpanis
RWRichard P. Wildes
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.