Related papers: ImageNet-X: Understanding Model Mistakes with Fact…

Despite significant recent progress, the best available computer vision algorithms still lag far behind human capabilities, even for recognizing individual discrete objects under various poses, illuminations, and backgrounds. Here we…

Image classifiers are information-discarding machines, by design. Yet, how these models discard information remains mysterious. We hypothesize that one way for image classifiers to reach high accuracy is to first zoom to the most…

Systematic error, which is not determined by chance, often refers to the inaccuracy (involving either the observation or measurement process) inherent to a system. In this paper, we exhibit some long-neglected but frequent-happening…

We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras. The dataset is collected using programmable hardware in which an event camera consistently moves around a monitor…

Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in modern computer vision research is that models that perform…

The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…

Human perception is routinely assessing the similarity between images, both for decision making and creative thinking. But the underlying cognitive process is not really well understood yet, hence difficult to be mimicked by computer vision…

Fundus photography is prone to suffer from image quality degradation that impacts clinical examination performed by ophthalmologists or intelligent systems. Though enhancement algorithms have been developed to promote fundus observation on…

In this paper, we present an empirical study on image recognition fairness, i.e., extreme class accuracy disparity on balanced data like ImageNet. We experimentally demonstrate that classes are not equal and the fairness issue is prevalent…

There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…

We focus on addressing the challenges in responsible beauty product recommendation, particularly when it involves comparing the product's color with a person's skin tone, such as for foundation and concealer products. To make accurate…

Deep neural networks have achieved success across a wide range of applications, including as models of human behavior and neural representations in vision tasks. However, neural network training and human learning differ in fundamental…

Rectifying the orientation of images represents a daily task for every photographer. This task may be complicated even for the human eye, especially when the horizon or other horizontal and vertical lines in the image are missing. In this…

Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations "data biases," and the visual features causing data…

We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using three well known DNNs (ResNet-152, VGG-19, GoogLeNet) we find…

When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

This paper investigates the impact of various data augmentation techniques on the performance of object detection models. Specifically, we explore classical augmentation methods, image compositing, and advanced generative models such as…

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

Variations in visual factors such as viewpoint, pose, illumination and background, are usually viewed as important challenges in person re-identification (re-ID). In spite of acknowledging these factors to be influential, quantitative…