In real-world classification tasks, each class often comprises multiple finer-grained “subclasses.” As the subclass labels are frequently unavailable, models trained using only the coarser-grained class labels often exhibit highly variable performance across different subclasses… This phenomenon, known as hidden stratification, has important consequences for models deployed in safety-critical applications such as medicine. We propose GEORGE, a method to both measure and mitigate hidden stratification even when subclass labels are unknown. We first observe that unlabeled subclasses are often separable in […]

TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK REMOVE Object Detection COCO test-dev GFLV2 (ResNet-50) box AP 44.3 # 45 Object Detection COCO test-dev GFLV2 (ResNet-50) AP50 62.3 # 54 Object Detection COCO test-dev GFLV2 (ResNet-50) AP75 48.5 # 47 Object Detection COCO test-dev GFLV2 (ResNet-50) APS 26.8  

This paper presents a comprehensive framework for studying methods of pulse rate estimation relying on remote photoplethysmography (rPPG). There has been a remarkable development of rPPG techniques in recent years, and the publication of several surveys too, yet a sound assessment of their performance has been overlooked at best, whether not undeveloped… The methodological rationale behind the framework we propose is that in order to study, develop and compare new rPPG methods in a principled and reproducible way, the following […]

Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) to represent the latent spaces of trained DNN architectures… Such graphs are obtained by connecting samples that yield similar latent representations at a given layer of the considered DNN. We then obtain a generalization score by looking at how strongly connected are samples of distinct classes in LGGs. This score […]

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance… Unfortunately, training such systems requires several hours of GPU time. For robots, to successfully adapt to changes in the environment or learning new objects, it is also important that object detectors can be re-trained in a short amount of time. A recent method [1] proposes an architecture that leverages on the powerful representation […]