Ali Borji
YOU?
Author Swipe
View article: Identifying Indicators of Optimizing Learning Environments Using Artificial Intelligence in Curriculum Design
Identifying Indicators of Optimizing Learning Environments Using Artificial Intelligence in Curriculum Design Open
This study aimed to identify key indicators for optimizing learning environments through the integration of artificial intelligence (AI) in curriculum design. A qualitative research design was employed, involving semi-structured interviews…
View article: A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'
A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data' Open
The study conducted by Shumailov et al. (2024) demonstrates that repeatedly training a generative model on synthetic data leads to model collapse. This finding has generated considerable interest and debate, particularly given that current…
View article: AIM 2024 Challenge on Video Saliency Prediction: Methods and Results
AIM 2024 Challenge on Video Saliency Prediction: Methods and Results Open
This paper reviews the Challenge on Video Saliency Prediction at AIM 2024. The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences. Saliency maps are widely exploit…
View article: Addressing a fundamental limitation in deep vision models: lack of spatial attention
Addressing a fundamental limitation in deep vision models: lack of spatial attention Open
The primary aim of this manuscript is to underscore a significant limitation in current deep learning models, particularly vision models. Unlike human vision, which efficiently selects only the essential visual areas for further processing…
View article: FLORIDA: Fake-looking Real Images Dataset
FLORIDA: Fake-looking Real Images Dataset Open
Although extensive research has been carried out to evaluate the effectiveness of AI tools and models in detecting deep fakes, the question remains unanswered regarding whether these models can accurately identify genuine images that appea…
View article: Key-Value Transformer
Key-Value Transformer Open
Transformers have emerged as the prevailing standard solution for various AI tasks, including computer vision and natural language processing. The widely adopted Query, Key, and Value formulation (QKV) has played a significant role in this…
View article: A Categorical Archive of ChatGPT Failures
A Categorical Archive of ChatGPT Failures Open
Large language models have been demonstrated to be valuable in different fields. ChatGPT, developed by OpenAI, has been trained using massive amounts of data and simulates human conversation by comprehending context and generating appropri…
View article: Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes Open
The ability of image and video generation models to create photorealistic images has reached unprecedented heights, making it difficult to distinguish between real and fake images in many cases. However, despite this progress, a gap remain…
View article: A Categorical Archive of ChatGPT Failures
A Categorical Archive of ChatGPT Failures Open
Large language models have been demonstrated to be valuable in different fields. ChatGPT, developed by OpenAI, has been trained using massive amounts of data and simulates human conversation by comprehending context and generating appropri…
View article: Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification Open
Test sets are an integral part of evaluating models and gauging progress in object recognition, and more broadly in computer vision and AI. Existing test sets for object recognition, however, suffer from shortcomings such as bias towards t…
View article: BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models
BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models Open
We introduce a new test set for visual question answering (VQA) called BinaryVQA to push the limits of VQA models. Our dataset includes 7,800 questions across 1,024 images and covers a wide variety of objects, topics, and concepts. For eas…
View article: Logits are predictive of network type
Logits are predictive of network type Open
We show that it is possible to predict which deep network has generated a given logit vector with accuracy well above chance. We utilize a number of networks on a dataset, initialized with random weights or pretrained weights, as well as f…
View article: Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2
Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2 Open
The field of image synthesis has made great strides in the last couple of years. Recent models are capable of generating images with astonishing quality. Fine-grained evaluation of these models on some interesting categories such as faces …
View article: How good are deep models in understanding the generated images?
How good are deep models in understanding the generated images? Open
My goal in this paper is twofold: to study how well deep models can understand the images generated by DALL-E 2 and Midjourney, and to quantitatively evaluate these generative models. Two sets of generated images are collected for object r…
View article: A New Kind of Adversarial Example
A New Kind of Adversarial Example Open
Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…
View article: Is current research on adversarial robustness addressing the right problem?
Is current research on adversarial robustness addressing the right problem? Open
Short answer: Yes, Long answer: No! Indeed, research on adversarial robustness has led to invaluable insights helping us understand and explore different aspects of the problem. Many attacks and defenses have been proposed over the last co…
View article: SplitMixer: Fat Trimmed From MLP-like Models
SplitMixer: Fat Trimmed From MLP-like Models Open
We present SplitMixer, a simple and lightweight isotropic MLP-like architecture, for visual recognition. It contains two types of interleaving convolutional operations to mix information across spatial locations (spatial mixing) and channe…
View article: Complementary datasets to COCO for object detection
Complementary datasets to COCO for object detection Open
For nearly a decade, the COCO dataset has been the central test bed of research in object detection. According to the recent benchmarks, however, it seems that performance on this dataset has started to saturate. One possible reason can be…
View article: Sensitivity of Average Precision to Bounding Box Perturbations
Sensitivity of Average Precision to Bounding Box Perturbations Open
Object detection is a fundamental vision task. It has been highly researched in academia and has been widely adopted in industry. Average Precision (AP) is the standard score for evaluating object detectors. Our understanding of the subtle…
View article: CNNs and Transformers Perceive Hybrid Images Similar to Humans
CNNs and Transformers Perceive Hybrid Images Similar to Humans Open
Hybrid images is a technique to generate images with two interpretations that change as a function of viewing distance. It has been utilized to study multiscale processing of images by the human visual system. Using 63,000 hybrid images ac…
View article: Overparametrization improves robustness against adversarial attacks: A replication study
Overparametrization improves robustness against adversarial attacks: A replication study Open
Overparametrization has become a de facto standard in machine learning. Despite numerous efforts, our understanding of how and where overparametrization helps model accuracy and robustness is still limited. To this end, here we conduct an …
View article: Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos
Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos Open
Visual and audio events simultaneously occur and both attract attention. However, most existing saliency prediction works ignore the influence of audio and only consider vision modality. In this paper, we propose a multitask learning metho…
View article: Shape Defense
Shape Defense Open
Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This fact is perhaps the main reason why CNNs are susceptible to adversarial examples. Here, w…
View article: Enhancing sensor resolution improves CNN accuracy given the same number of parameters or FLOPS
Enhancing sensor resolution improves CNN accuracy given the same number of parameters or FLOPS Open
High image resolution is critical to obtain a good performance in many computer vision applications. Computational complexity of CNNs, however, grows significantly with the increase in input image size. Here, we show that it is almost alwa…
View article: Contemplating real-world object classification
Contemplating real-world object classification Open
Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this pr…
View article: Contemplating real-world object classification
Contemplating real-world object classification Open
Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this pr…