Related papers: Attribution in Scale and Space

The computer vision community is witnessing an unprecedented rate of new tasks being proposed and addressed, thanks to the deep convolutional networks' capability to find complex mappings from X to Y. The advent of each task often…

We propose a method that efficiently learns distributions over articulation model parameters directly from depth images without the need to know articulation model categories a priori. By contrast, existing methods that learn articulation…

Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures. Many such structured-prediction problems require…

The human visual system excels at detecting local blur of visual images, but the underlying mechanism is not well understood. Traditional views of blur such as reduction in energy at high frequencies and loss of phase coherence at localized…

Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often…

Humans and many animals show remarkably adaptive behavior and can respond differently to the same input depending on their internal goals. The brain not only represents the intermediate abstractions needed to perform a computation but also…

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the…

Attribution methods explain neural network predictions by identifying influential input features, but their evaluation suffers from threshold selection bias that can reverse method rankings and undermine conclusions. Current protocols…

Feature attribution has been a foundational building block for explaining the input feature importance in supervised learning with Deep Neural Network (DNNs), but face new challenges when applied to deep Reinforcement Learning (RL).We…

Integrated Gradients is a well-known technique for explaining deep learning models. It calculates feature importance scores by employing a gradient based approach computing gradients of the model output with respect to input features and…

A major challenge in scene graph classification is that the appearance of objects and relations can be significantly different from one image to another. Previous works have addressed this by relational reasoning over all objects in an…

Learning implicit representations has been a widely used solution for surface reconstruction from 3D point clouds. The latest methods infer a distance or occupancy field by overfitting a neural network on a single point cloud. However,…

Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained…

As interpretability has been pointed out as the obstacle to the adoption of Deep Neural Networks (DNNs), there is an increasing interest in solving a transparency issue to guarantee the impressive performance. In this paper, we demonstrate…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Open set recognition (OSR) is devised to address the problem of detecting novel classes during model inference. Even in recent vision models, this remains an open issue which is receiving increasing attention. Thereby, a crucial challenge…

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…

Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image…

Large-scale visual place recognition (VPR) is inherently challenging because not all visual cues in the image are beneficial to the task. In order to highlight the task-relevant visual cues in the feature embedding, the existing attention…

Incorporating multi-scale features in fully convolutional neural networks (FCNs) has been a key element to achieving state-of-the-art performance on semantic image segmentation. One common way to extract multi-scale features is to feed…