Ahmad Nickabadi

Ahmad Nickabadi, Maryam Saeedi Fard, Nastaran Moradzadeh Farid et al.

Generating random photo-realistic images has experienced tremendous growth during the past few years due to the advances of the deep convolutional neural networks and generative models. Among different domains, face photos have received a great deal of attention and a large number of face generation and manipulation models have been proposed. Semantic facial attribute editing is the process of varying the values of one or more attributes of a face image while the other attributes of the image are not affected. The requested modifications are provided as an attribute vector or in the form of driving face image and the whole process is performed by the corresponding models. In this paper, we survey the recent works and advances in semantic facial attribute editing. We cover all related aspects of these models including the related definitions and concepts, architectures, loss functions, datasets, evaluation metrics, and applications. Based on their architectures, the state-of-the-art models are categorized and studied as encoder-decoder, image-to-image, and photo-guided models. The challenges and restrictions of the current state-of-the-art methods are discussed as well.

Najmeh Mohammadbagheri, Fardin Ayar, Ahmad Nickabadi et al.

Semantic facial attribute editing using pre-trained Generative Adversarial Networks (GANs) has attracted a great deal of attention and effort from researchers in recent years. Due to the high quality of face images generated by StyleGANs, much work has focused on the StyleGANs' latent space and the proposed methods for facial image editing. Although these methods have achieved satisfying results for manipulating user-intended attributes, they have not fulfilled the goal of preserving the identity, which is an important challenge. We present ID-Style, a new architecture capable of addressing the problem of identity loss during attribute manipulation. The key components of ID-Style include Learnable Global Direction (LGD), which finds a shared and semi-sparse direction for each attribute, and an Instance-Aware Intensity Predictor (IAIP) network, which finetunes the global direction according to the input instance. Furthermore, we introduce two losses during training to enforce the LGD to find semi-sparse semantic directions, which along with the IAIP, preserve the identity of the input instance. Despite reducing the size of the network by roughly 95% as compared to similar state-of-the-art works, it outperforms baselines by 10% and 7% in Identity preserving metric (FRS) and average accuracy of manipulation (mACC), respectively.

Mohammad Javad Rajabi, Morteza Mirzai, Ahmad Nickabadi

Visual place recognition tasks often encounter significant challenges in landmark detection due to the presence of irrelevant objects such as humans, cars, and trees, despite the remarkable progress achieved by previous models, especially in the context of transformers. To address this issue, we propose a novel method that effectively leverages the strengths of vision transformers. By employing a meticulous selection process, our approach identifies and isolates specific patches within the image that correspond to occluding objects. To evaluate the efficacy of our method, we created augmented datasets and conducted comprehensive testing. The results demonstrate the superior accuracy achieved by our proposed approach. This research contributes to the advancement of landmark detection in visual place recognition and shows the potential of leveraging vision transformers to overcome challenges posed by cluttered real-world scenarios.

Omid Saghatchian, Atiyeh Gh. Moghadam, Ahmad Nickabadi

Diffusion models have emerged as a promising approach for generating high-quality, high-dimensional images. Nevertheless, these models are hindered by their high computational cost and slow inference, partly due to the quadratic computational complexity of the self-attention mechanisms with respect to input size. Various approaches have been proposed to address this drawback. One such approach focuses on reducing the number of tokens fed into the self-attention, known as token merging (ToMe). In our method, which is called cached adaptive token merging(CA-ToMe), we calculate the similarity between tokens and then merge the r proportion of the most similar tokens. However, due to the repetitive patterns observed in adjacent steps and the variation in the frequency of similarities, we aim to enhance this approach by implementing an adaptive threshold for merging tokens and adding a caching mechanism that stores similar pairs across several adjacent steps. Empirical results demonstrate that our method operates as a training-free acceleration method, achieving a speedup factor of 1.24 in the denoising process while maintaining the same FID scores compared to existing approaches.

Ali Samadzadeh, Mohammad Hassan Mojab, Heydar Soudani et al.

Visual Inertial Odometry (VIO) algorithms estimate the accurate camera trajectory by using camera and Inertial Measurement Unit (IMU) sensors. The applications of VIO span a diverse range, including augmented reality and indoor navigation. VIO algorithms hold the potential to facilitate navigation for visually impaired individuals in both indoor and outdoor settings. Nevertheless, state-of-the-art VIO algorithms encounter substantial challenges in dynamic environments, particularly in densely populated corridors. Existing VIO datasets, e.g., ADVIO, typically fail to effectively exploit these challenges. In this paper, we introduce the Amirkabir campus dataset (AUT-VI) to address the mentioned problem and improve the navigation systems. AUT-VI is a novel and super-challenging dataset with 126 diverse sequences in 17 different locations. This dataset contains dynamic objects, challenging loop-closure/map-reuse, different lighting conditions, reflections, and sudden camera movements to cover all extreme navigation scenarios. Moreover, in support of ongoing development efforts, we have released the Android application for data capture to the public. This allows fellow researchers to easily capture their customized VIO dataset variations. In addition, we evaluate state-of-the-art Visual Inertial Odometry (VIO) and Visual Odometry (VO) methods on our dataset, emphasizing the essential need for this challenging dataset.

Ali Samadzadeh, Ahmad Nickabadi

There has been extensive research on visual localization and odometry for autonomous robots and virtual reality during the past decades. Traditionally, this problem has been solved with the help of expensive sensors, such as lidars. Nowadays, the focus of the leading research in this field is on robust localization using more economic sensors, such as cameras and IMUs. Consequently, geometric visual localization methods have become more accurate in time. However, these methods still suffer from significant loss and divergence in challenging environments, such as a room full of moving people. Scientists started using deep neural networks (DNNs) to mitigate this problem. The main idea behind using DNNs is to better understand challenging aspects of the data and overcome complex conditions such as the movement of a dynamic object in front of the camera that covers the full view of the camera, extreme lighting conditions, and high speed of the camera. Prior end-to-end DNN methods have overcome some of these challenges. However, no general and robust framework is available to overcome all challenges together. In this paper, we have combined geometric and DNN-based methods to have the generality and speed of geometric SLAM frameworks and overcome most of these challenging conditions with the help of DNNs and deliver the most robust framework so far. To do so, we have designed a framework based on Vins-Mono, and show that it is able to achieve state-of-the-art results on TUM-Dynamic, TUM-VI, ADVIO, and EuRoC datasets compared to geometric and end-to-end DNN based SLAMs. Our proposed framework could also achieve outstanding results on extreme simulated cases resembling the aforementioned challenges.

Mohammad Hossein Khojaste, Nastaran Moradzadeh Farid, Ahmad Nickabadi

The use of social media websites and applications has become very popular and people share their photos on these networks. Automatic recognition and tagging of people's photos on these networks has raised privacy preservation issues and users seek methods for hiding their identities from these algorithms. Generative adversarial networks (GANs) are shown to be very powerful in generating face images in high diversity and also in editing face images. In this paper, we propose a Generative Mask-guided Face Image Manipulation (GMFIM) model based on GANs to apply imperceptible editing to the input face image to preserve the privacy of the person in the image. Our model consists of three main components: a) the face mask module to cut the face area out of the input image and omit the background, b) the GAN-based optimization module for manipulating the face image and hiding the identity and, c) the merge module for combining the background of the input image and the manipulated de-identified face image. Different criteria are considered in the loss function of the optimization step to produce high-quality images that are as similar as possible to the input image while they cannot be recognized by AFR systems. The results of the experiments on different datasets show that our model can achieve better performance against automated face recognition systems in comparison to the state-of-the-art methods and it catches a higher attack success rate in most experiments from a total of 18. Moreover, the generated images of our proposed model have the highest quality and are more pleasing to human eyes.

Nastaran Moradzadeh Farid, Maryam Saeedi Fard, Ahmad Nickabadi

Translating face sketches to photo-realistic faces is an interesting and essential task in many applications like law enforcement and the digital entertainment industry. One of the most important challenges of this task is the inherent differences between the sketch and the real image such as the lack of color and details of the skin tissue in the sketch. With the advent of adversarial generative models, an increasing number of methods have been proposed for sketch-to-image synthesis. However, these models still suffer from limitations such as the large number of paired data required for training, the low resolution of the produced images, or the unrealistic appearance of the generated images. In this paper, we propose a method for converting an input facial sketch to a colorful photo without the need for any paired dataset. To do so, we use a pre-trained face photo generating model to synthesize high-quality natural face photos and employ an optimization procedure to keep high-fidelity to the input sketch. We train a network to map the facial features extracted from the input sketch to a vector in the latent space of the face generating model. Also, we study different optimization criteria and compare the results of the proposed model with those of the state-of-the-art models quantitatively and qualitatively. The proposed model achieved 0.655 in the SSIM index and 97.59% rank-1 face recognition rate with higher quality of the produced images.

Amir Mohammad Rostami, Mohammad Mehdi Homayounpour, Ahmad Nickabadi

Many endeavors have sought to develop countermeasure techniques as enhancements on Automatic Speaker Verification (ASV) systems, in order to make them more robust against spoof attacks. As evidenced by the latest ASVspoof 2019 countermeasure challenge, models currently deployed for the task of ASV are, at their best, devoid of suitable degrees of generalization to unseen attacks. Upon further investigation of the proposed methods, it appears that a broader three-tiered view of the proposed systems. comprised of the classifier, feature extraction phase, and model loss function, may to some extent lessen the problem. Accordingly, the present study proposes the Efficient Attention Branch Network (EABN) modular architecture with a combined loss function to address the generalization problem...

Fatemeh Vakhshiteh, Ahmad Nickabadi, Raghavendra Ramachandra

Face recognition (FR) systems have demonstrated outstanding verification performance, suggesting suitability for real-world applications ranging from photo tagging in social media to automated border control (ABC). In an advanced FR system with deep learning-based architecture, however, promoting the recognition efficiency alone is not sufficient, and the system should also withstand potential kinds of attacks designed to target its proficiency. Recent studies show that (deep) FR systems exhibit an intriguing vulnerability to imperceptible or perceptible but natural-looking adversarial input images that drive the model to incorrect output predictions. In this article, we present a comprehensive survey on adversarial attacks against FR systems and elaborate on the competence of new countermeasures against them. Further, we propose a taxonomy of existing attack and defense methods based on different criteria. We compare attack methods on the orientation and attributes and defense approaches on the category. Finally, we explore the challenges and potential research direction.

Marzieh Heidari, Mehdi Ghatee, Ahmad Nickabadi et al.

With great advances in vision and natural language processing, the generation of image captions becomes a need. In a recent paper, Mathews, Xie and He [1], extended a new model to generate styled captions by separating semantics and style. In continuation of this work, here a new captioning model is developed including an image encoder to extract the features, a mixture of recurrent networks to embed the set of extracted features to a set of words, and a sentence generator that combines the obtained words as a stylized sentence. The resulted system that entitled as Mixture of Recurrent Experts (MoRE), uses a new training algorithm that derives singular value decomposition (SVD) from weighting matrices of Recurrent Neural Networks (RNNs) to increase the diversity of captions. Each decomposition step depends on a distinctive factor based on the number of RNNs in MoRE. Since the used sentence generator gives a stylized language corpus without paired images, our captioning model can do the same. Besides, the styled and diverse captions are extracted without training on a densely labeled or styled dataset. To validate this captioning model, we use Microsoft COCO which is a standard factual image caption dataset. We show that the proposed captioning model can generate a diverse and stylized image captions without the necessity of extra-labeling. The results also show better descriptions in terms of content accuracy.

Ali Samadzadeh, Fatemeh Sadat Tabatabaei Far, Ali Javadi et al.

Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature. Also, they have the advantage of low computation cost in contrast to conventional artificial neural networks (ANNs), while preserving ANN's properties. However, temporal coding in layers of convolutional spiking neural networks and other types of SNNs has yet to be studied. In this paper, we provide insight into spatio-temporal feature extraction of convolutional SNNs in experiments designed to exploit this property. The shallow convolutional SNN outperforms state-of-the-art spatio-temporal feature extractor methods such as C3D, ConvLstm, and similar networks. Furthermore, we present a new deep spiking architecture to tackle real-world problems (in particular classification tasks) which achieved superior performance compared to other SNN methods on NMNIST (99.6%), DVS-CIFAR10 (69.2%) and DVS-Gesture (96.7%) and ANN methods on UCF-101 (42.1%) and HMDB-51 (21.5%) datasets. It is also worth noting that the training process is implemented based on variation of spatio-temporal backpropagation explained in the paper.

Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi et al.

We present an end-to-end deep Convolutional Neural Network called Convolutional Relational Machine (CRM) for recognizing group activities that utilizes the information in spatial relations between individual persons in image or video. It learns to produce an intermediate spatial representation (activity map) based on individual and group activities. A multi-stage refinement component is responsible for decreasing the incorrect predictions in the activity map. Finally, an aggregation component uses the refined information to recognize group activities. Experimental results demonstrate the constructive contribution of the information extracted and represented in the form of the activity map. CRM shows advantages over state-of-the-art models on Volleyball and Collective Activity datasets.

Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi

In this work, we present a framework based on multi-stream convolutional neural networks (CNNs) for group activity recognition. Streams of CNNs are separately trained on different modalities and their predictions are fused at the end. Each stream has two branches to predict the group activity based on person and scene level representations. A new modality based on the human pose estimation is presented to add extra information to the model. We evaluate our method on the Volleyball and Collective Activity datasets. Experimental results show that the proposed framework is able to achieve state-of-the-art results when multiple or single frames are given as input to the model with 90.50% and 86.61% accuracy on Volleyball dataset, respectively, and 87.01% accuracy of multiple frames group activity on Collective Activity dataset.

Sina Mokhtarzadeh Azar, Sajjad Azami, Mina Ghadimi Atigh et al.

The overwhelming popularity of social media has resulted in bulk amounts of personal photos being uploaded to the internet every day. Since these photos are taken in unconstrained settings, recognizing the identities of people among the photos remains a challenge. Studies have indicated that utilizing evidence other than face appearance improves the performance of person recognition systems. In this work, we aim to take advantage of additional cues obtained from different body regions in a zooming in fashion for person recognition. Hence, we present Zoom-RNN, a novel method based on recurrent neural networks for combining evidence extracted from the whole body, upper body, and head regions. Our model is evaluated on a challenging dataset, namely People In Photo Albums (PIPA), and we demonstrate that employing our system improves the performance of conventional fusion methods by a noticeable margin.

Mohammad Pezeshki, Sajjad Gholami, Ahmad Nickabadi

Data representation is an important pre-processing step in many machine learning algorithms. There are a number of methods used for this task such as Deep Belief Networks (DBNs) and Discrete Fourier Transforms (DFTs). Since some of the features extracted using automated feature extraction methods may not always be related to a specific machine learning task, in this paper we propose two methods in order to make a distinction between extracted features based on their relevancy to the task. We applied these two methods to a Deep Belief Network trained for a face recognition task.