1.4k citations · 4.4k across the 74 of their papers we have counts for
77 papers · 1 filter
A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection
Ali Borji
Almost all adversarial attacks add an imperceptible perturbation to fool a model. We instead study the opposite: a large, clearly visible perturbation that causes the model to keep…
Addressing a fundamental limitation in deep vision models: lack of spatial attention
Ali Borji
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 sel…
Key-Value Transformer
Ali Borji
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 Va…
Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
Ali Borji
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…
Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
Ali Borji
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 recognitio…
BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models
Ali Borji
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 cove…
Logits are predictive of network type
Ali Borji
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, initiali…
Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2
Ali Borji
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…
How good are deep models in understanding the generated images?
Ali Borji
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 mode…
A New Kind of Adversarial Example
Ali Borji
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 example…
Is current research on adversarial robustness addressing the right problem?
Ali Borji
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. Ma…
SplitMixer: Fat Trimmed From MLP-like Models
Ali Borji, Sikun Lin
We present SplitMixer, a simple and lightweight isotropic MLP-like architecture, for visual recognition. It contains two types of interleaving convolutional operations to mix infor…
Complementary datasets to COCO for object detection
Ali Borji
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…
Sensitivity of Average Precision to Bounding Box Perturbations
Ali Borji
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 e…
CNNs and Transformers Perceive Hybrid Images Similar to Humans
Ali Borji
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 image…
Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos
Minglang Qiao, Yufan Liu, Mai Xu +4
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 mod…
Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model
Yufan Liu, Minglang Qiao, Mai Xu +3
Recently, video streams have occupied a large proportion of Internet traffic, most of which contain human faces. Hence, it is necessary to predict saliency on multiple-face videos,…
Contemplating real-world object classification
Ali Borji
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…
Enhancing sensor resolution improves CNN accuracy given the same number of parameters or FLOPS
Ali Borji
High image resolution is critical to obtain a good performance in many computer vision applications. Computational complexity of CNNs, however, grows significantly with the increas…
A Compact Deep Architecture for Real-time Saliency Prediction
Saman Zabihi, Hamed Rezazadegan Tavakoli, Ali Borji
Saliency computation models aim to imitate the attention mechanism in the human visual system. The application of deep neural networks for saliency prediction has led to a drastic…
Shape Defense Against Adversarial Attacks
Ali Borji
Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why…
Bifurcated backbone strategy for RGB-D salient object detection
Yingjie Zhai, Deng-Ping Fan, Jufeng Yang +4
Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features mee…
Adversarial examples are useful too!
Ali Borji
Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversari…
Empirical Upper Bound, Error Diagnosis and Invariance Analysis of Modern Object Detectors
Ali Borji
Object detection remains as one of the most notorious open problems in computer vision. Despite large strides in accuracy in recent years, modern object detectors have started to s…