Related papers: Corner Cases: How Size and Position of Objects Cha…
Training dataset biases are by far the most scrutinized factors when explaining algorithmic biases of neural networks. In contrast, hyperparameters related to the neural network architecture have largely been ignored even though different…
A common problem in data analysis is that the functional form, as well as the parameter values, of the underlying model which should describe a dataset is not known a priori. In these cases some extra uncertainty must be assigned to the…
Recent research used machine learning methods to predict a person's sexual orientation from their photograph (Wang and Kosinski, 2017). To verify this result, two of these models are replicated, one based on a deep neural network (DNN) and…
Computer vision applications based on videos often require the detection of moving objects in their first step. Background subtraction is then applied in order to separate the background and the foreground. In literature, background…
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…
In this paper, we study the problem of unsupervised object segmentation from single images. We do not introduce a new algorithm, but systematically investigate the effectiveness of existing unsupervised models on challenging real-world…
Observational studies of causal effects require adjustment for confounding factors. In the tabular setting, where these factors are well-defined, separate random variables, the effect of confounding is well understood. However, in public…
As model and dataset sizes continue to scale in robot learning, the need to understand how the composition and properties of a dataset affect model performance becomes increasingly urgent to ensure cost-effective data collection and model…
Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come from? We find that, when trained on datasets of images with…
This work aims to explore and identify tiny and seemingly unrelated perturbations of images in object detection that will lead to performance degradation. While tininess can naturally be defined using $L_p$ norms, we characterize the degree…
We provide a comprehensive evaluation of salient object detection (SOD) models. Our analysis identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in…
Both a good understanding of geometrical concepts and a broad familiarity with objects lead to our excellent perception of moving objects. The human ability to detect and segment moving objects works in the presence of multiple objects,…
In recent years, three-dimensional point clouds are used increasingly to document natural environments. Each dataset contains a diverse set of objects, at varying shapes and sizes, distributed throughout the data and intricately intertwined…
Intelligent systems possess a crucial characteristic of breaking complicated problems into smaller reusable components or parts and adjusting to new tasks using these part representations. However, current part-learners encounter…
Background fluorescence, especially when it exhibits undesired spatial features, is a primary factor for reduced image quality in optical microscopy. Structured background is particularly detrimental when analyzing single-molecule images…
Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into a significant topic in recent years. However, images with…
Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relation. Relying on those correlations leads to poor performance in the data groups without these…
A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person. While this center-point regression is simple and efficient, we argue that the…
In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images. However, most Convolutional Neural Networks (CNNs) for image classification were…
Contrast is subject to dramatic changes across the visual field, depending on the source of light and scene configurations. Hence, the human visual system has evolved to be more sensitive to contrast than absolute luminance. This feature is…