相关论文: Uncertainty-Aware Perceiver

Rapid advances in perception have enabled large pre-trained models to be used out of the box for transforming high-dimensional, noisy, and partial observations of the world into rich occupancy representations. However, the reliability of…

Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression. However, the most commonly used autoregressive models, Transformers, are prohibitively…

Modern computer systems are highly configurable, with the total variability space sometimes larger than the number of atoms in the universe. Understanding and reasoning about the performance behavior of highly configurable systems, over a…

Deep learning models frequently encounter feature uncertainty in diverse learning scenarios, significantly impacting their performance and reliability. This challenge is particularly complex in multi-modal scenarios, where models must…

The superior performance of some of today's state-of-the-art deep learning models is to some extent owed to extensive (self-)supervised contrastive pretraining on large-scale datasets. In contrastive learning, the network is presented with…

When solving forecasting problems including multiple time-series features, existing approaches often fall into two extreme categories, depending on whether to utilize inter-feature information: univariate and complete-multivariate models.…

The human ability to recognize when an object belongs or does not belong to a particular vision task outperforms all open set recognition algorithms. Human perception as measured by the methods and procedures of visual psychophysics from…

Transformers have been matching deep convolutional networks for vision architectures in recent works. Most work is focused on getting the best results on large-scale benchmarks, and scaling laws seem to be the most successful strategy:…

Much effort has been devoted to making large and more accurate models, but relatively little has been put into understanding which examples are benefiting from the added complexity. In this paper, we demonstrate and analyze the surprisingly…

Safety-critical perception systems require both reliable uncertainty quantification and principled abstention mechanisms to maintain safety under diverse operational conditions. We present a novel dual-threshold conformalization framework…

Machine learning advances in the last decade have relied significantly on large-scale datasets that continue to grow in size. Increasingly, those datasets also contain different data modalities. However, large multi-modal datasets are hard…

The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance. From the perspective of accuracy, pattern recognition seems to be a nearly-solved problem. However,…

Contrastive approaches to representation learning have recently shown great promise. In contrast to generative approaches, these contrastive models learn a deterministic encoder with no notion of uncertainty or confidence. In this paper, we…

Modern buildings consist of hundreds of sensors and actuators for monitoring and operation of systems such as HVAC, light and security. To enable portable applications in next generation smart buildings, we need models and standardized…

Understanding the perceptual invariances of artificial neural networks is essential for improving explainability and aligning models with human vision. Metamers - stimuli that are physically distinct yet produce identical neural activations…

Due to the comprehensive nature of this paper, it has been updated and split into two separate papers: "A Framework For Benchmarking Class-out-of-distribution Detection And Its Application To ImageNet" and "What Can We Learn From The…

Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneous reliability of individual predictions. Furthermore, the…

In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on…

Vision Transformers have excelled in computer vision but their attention mechanisms operate independently across layers, limiting information flow and feature learning. We propose an effective cross-layer attention propagation method that…

This paper introduces the first theoretical framework for quantifying the efficiency and performance gain opportunity size of adaptive inference algorithms. We provide new approximate and exact bounds for the achievable efficiency and…