no code implementations • 2 Mar 2024 • Lian Xu, Mohammed Bennamoun, Farid Boussaid, Wanli Ouyang, Ferdous Sohel, Dan Xu
We propose AuxSegNet+, a weakly supervised auxiliary learning framework to explore the rich information from these saliency maps and the significant inter-task correlation between saliency detection and semantic segmentation.
no code implementations • 27 Feb 2024 • Ashkan Taghipour, Morteza Ghahremani, Mohammed Bennamoun, Aref Miri Rekavandi, Hamid Laga, Farid Boussaid
To address these deficiencies, we introduce the Box-it-to-Bind-it (B2B) module - a novel, training-free approach for improving spatial control and semantic accuracy in text-to-image (T2I) diffusion models.
1 code implementation • 10 Sep 2023 • Aref Miri Rekavandi, Shima Rashidi, Farid Boussaid, Stephen Hoefs, Emre Akbas, Mohammed Bennamoun
Transformers have rapidly gained popularity in computer vision, especially in the field of object recognition and detection.
1 code implementation • 6 Aug 2023 • Lian Xu, Mohammed Bennamoun, Farid Boussaid, Hamid Laga, Wanli Ouyang, Dan Xu
Building upon the observation that the attended regions of the one-class token in the standard vision transformer can contribute to a class-agnostic localization map, we explore the potential of the transformer model to capture class-specific attention for class-discriminative object localization by learning multiple class tokens.
Object Localization Weakly supervised Semantic Segmentation +1
no code implementations • 9 Mar 2023 • Hao Tang, Aref Miri Rekavandi, Dharjinder Rooprai, Girish Dwivedi, Frank Sanfilippo, Farid Boussaid, Mohammed Bennamoun
This study investigates the effectiveness of Explainable Artificial Intelligence (XAI) techniques in predicting suicide risks and identifying the dominant causes for such behaviours.
no code implementations • ICCV 2023 • Zhiheng Fu, Longguang Wang, Lian Xu, Zhiyong Wang, Hamid Laga, Yulan Guo, Farid Boussaid, Mohammed Bennamoun
In this paper, we thus propose an unsupervised viewpoint representation learning scheme for 3D point cloud completion without explicit viewpoint estimation.
no code implementations • CVPR 2023 • Lian Xu, Wanli Ouyang, Mohammed Bennamoun, Farid Boussaid, Dan Xu
Weakly supervised dense object localization (WSDOL) relies generally on Class Activation Mapping (CAM), which exploits the correlation between the class weights of the image classifier and the pixel-level features.
1 code implementation • 12 Oct 2022 • Yanbin Liu, Girish Dwivedi, Farid Boussaid, Mohammed Bennamoun
Generative models such as generative adversarial networks and autoencoders have gained a great deal of attention in the medical field due to their excellent data generation capability.
no code implementations • 17 Sep 2022 • Laurent Jospin, Allen Antony, Lian Xu, Hamid Laga, Farid Boussaid, Mohammed Bennamoun
In this paper, we propose the Active-Passive SimStereo dataset and a corresponding benchmark to evaluate the performance gap between passive and active stereo images for stereo matching algorithms.
no code implementations • 12 Sep 2022 • Laurent Valentin Jospin, Hamid Laga, Farid Boussaid, Mohammed Bennamoun
A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision.
no code implementations • 8 Aug 2022 • Yanbin Liu, Girish Dwivedi, Farid Boussaid, Frank Sanfilippo, Makoto Yamada, Mohammed Bennamoun
Novel 3D network architectures are proposed for both the generator and discriminator of the GAN model to significantly reduce the number of parameters while maintaining the quality of image generation.
no code implementations • 26 Jul 2022 • Aref Miri Rekavandi, Lian Xu, Farid Boussaid, Abd-Krim Seghouane, Stephen Hoefs, Mohammed Bennamoun
Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects.
no code implementations • 9 Jul 2022 • Lin Wu, Lingqiao Liu, Yang Wang, Zheng Zhang, Farid Boussaid, Mohammed Bennamoun
It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras.
no code implementations • 9 Jul 2022 • Lin Wu, Deyin Liu, Wenying Zhang, Dapeng Chen, ZongYuan Ge, Farid Boussaid, Mohammed Bennamoun, Jialie Shen
In this paper, we present a pseudo-pair based self-similarity learning approach for unsupervised person re-ID without human annotations.
no code implementations • 9 Jul 2022 • Deyin Liu, Lin Wu, Haifeng Zhao, Farid Boussaid, Mohammed Bennamoun, Xianghua Xie
Moreover, adversarially training a defense model in general cannot produce interpretable predictions towards the inputs with perturbations, whilst a highly interpretable robust model is required by different domain experts to understand the behaviour of a DNN.
1 code implementation • 24 Mar 2022 • Mohammed Hassanin, Abdelwahed Khamiss, Mohammed Bennamoun, Farid Boussaid, Ibrahim Radwan
3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints.
Ranked #24 on 3D Human Pose Estimation on Human3.6M
1 code implementation • CVPR 2022 • Lian Xu, Wanli Ouyang, Mohammed Bennamoun, Farid Boussaid, Dan Xu
To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens.
1 code implementation • 2 Dec 2021 • Laurent Valentin Jospin, Farid Boussaid, Hamid Laga, Mohammed Bennamoun
In this paper, we show that closed form formulae for subpixel disparity computation for the case of one dimensional matching, e. g., in the case of rectified stereo images where the search space is of one dimension, exists when using the standard NCC, SSD and SAD cost functions.
1 code implementation • ICCV 2021 • Lian Xu, Wanli Ouyang, Mohammed Bennamoun, Farid Boussaid, Ferdous Sohel, Dan Xu
Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels.
4 code implementations • 14 Jul 2020 • Laurent Valentin Jospin, Wray Buntine, Farid Boussaid, Hamid Laga, Mohammed Bennamoun
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems.
no code implementations • 1 Jun 2020 • Hamid Laga, Laurent Valentin Jospin, Farid Boussaid, Mohammed Bennamoun
Motivated by their growing success in solving various 2D and 3D vision problems, deep learning for stereo-based depth estimation has attracted growing interest from the community, with more than 150 papers published in this area between 2014 and 2019.
Ranked #1 on Monocular Depth Estimation on Make3D (RMSE metric)
no code implementations • IEEE Transactions on Image Processing 2019 • Qiuhong Ke, Mohammed Bennamoun, Hossein Rahmani, Senjian An, Ferdous Sohel, Farid Boussaid
Human actions represented with 3D skeleton sequences are robust to clustered backgrounds and illumination changes.
Ranked #4 on Skeleton Based Action Recognition on SYSU 3D
no code implementations • 26 Jun 2019 • Ammar Mahmood, Ana Giraldo Ospina, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid, Renae Hovey, Robert B. Fisher, Gary Kendrick
Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas.
no code implementations • IEEE Transactions on Image Processing ( Volume: 27 , Issue: 6 , June 2018 ) 2018 • Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid
This paper presents a new representation of skeleton sequences for 3D action recognition.
Ranked #60 on Skeleton Based Action Recognition on NTU RGB+D 120
no code implementations • 14 Nov 2017 • Senjian An, Farid Boussaid, Mohammed Bennamoun, Ferdous Sohel
By introducing sign constraints on the weights, this paper proposes sign constrained rectifier networks (SCRNs), whose training can be solved efficiently by the well known majorization-minimization (MM) algorithms.
no code implementations • 24 Aug 2017 • Senjian An, Mohammed Bennamoun, Farid Boussaid
To show the superior compressive power of deep rectifier networks over shallow rectifier networks, we prove that the maximum boundary resolution of a single hidden layer rectifier network classifier grows exponentially with the number of units when this number is smaller than the dimension of the patterns.
no code implementations • IEEE Signal Processing Letters ( Volume: 24 , Issue: 6 , June 2017 ) 2017 • Qiuhong Ke, Senjian An, Mohammed Bennamoun, Ferdous Sohel, Farid Boussaid
Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition.
Ranked #106 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • 30 Mar 2017 • Senjian An, Farid Boussaid, Mohammed Bennamoun, Jiankun Hu
Similarly, for a residual net and a conventional rectifier net with the same structure except for the skip connections in the residual net, the corresponding single hidden layer representation of the residual net is much more complex than the corresponding single hidden layer representation of the conventional net.
no code implementations • CVPR 2017 • Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid
This paper presents a new method for 3D action recognition with skeleton sequences (i. e., 3D trajectories of human skeleton joints).
Ranked #65 on Skeleton Based Action Recognition on NTU RGB+D 120
no code implementations • ICCV 2015 • Senjian An, Munawar Hayat, Salman H. Khan, Mohammed Bennamoun, Farid Boussaid, Ferdous Sohel
The contractive constraints ensure that the achieved separating margin in the input space is larger than or equal to the separating margin in the output layer.