相关论文: Look at the Variance! Efficient Black-box Explanat…

Global sensitivity analysis (GSA) aims at quantifying the contribution of input variables over the variability of model outputs. In the frame of functional outputs, a common goal is to compute sensitivity maps (SM), i.e sensitivity indices…

Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…

Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to localize objects using image level annotations indirectly.…

Deep neural networks have achieved great success in many real-world applications, yet it remains unclear and difficult to explain their decision-making process to an end-user. In this paper, we address the explainable AI problem for deep…

Among the many estimators of first order Sobol indices that have been proposed in the literature, the so-called rank-based estimator is arguably the simplest to implement. This estimator can be viewed as the empirical auto-correlation of…

Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes. This task plays an important role in self-driving cars and autonomous drones. In SS, many works have shown that most misclassified pixels are…

We propose a new statistical estimation framework for a large family of global sensitivity analysis methods. Our approach is based on rank statistics and uses an empirical correlation coefficient recently introduced by Sourav Chatterjee. We…

Black box models in machine learning have demonstrated excellent predictive performance in complex problems and high-dimensional settings. However, their lack of transparency and interpretability restrict the applicability of such models in…

We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or…

A central problem in hyperspectral image classification is obtaining high classification accuracy when using a limited amount of labelled data. In this paper we present a novel graph-based framework, which aims to tackle this problem in the…

Planet-scale photo geolocalization is the complex task of estimating the location depicted in an image solely based on its visual content. Due to the success of convolutional neural networks (CNNs), current approaches achieve super-human…

The Trotter-Suzuki decomposition is one of the main approaches for realization of quantum simulations on digital quantum computers. Variance-based global sensitivity analysis (the Sobol method) is a wide used method which allows to…

We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is…

Attribution methods shed light on the explainability of data-driven approaches such as deep learning models by uncovering the most influential features in a to-be-explained decision. While determining feature attributions via gradients…

Current object detection frameworks mainly rely on bounding box regression to localize objects. Despite the remarkable progress in recent years, the precision of bounding box regression remains unsatisfactory, hence limiting performance in…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

We propose an approach to instance-level image segmentation that is built on top of category-level segmentation. Specifically, for each pixel in a semantic category mask, its corresponding instance bounding box is predicted using a deep…

Recently many multi-label image recognition (MLR) works have made significant progress by introducing pre-trained object detection models to generate lots of proposals or utilizing statistical label co-occurrence enhance the correlation…

Weakly supervised object detection aims at learning precise object detectors, given image category labels. In recent prevailing works, this problem is generally formulated as a multiple instance learning module guided by an image…