Genre
Benchmarking the Attribution Quality of Vision Models Robin Hesse 1 Simone Schaub-Meyer 1,2 Stefan Roth 1,2 1 Department of Computer Science, Technical University of Darmstadt
Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural network.
Statistical-ComputationalTrade-offsforDensity Estimation
Inparticular,ifanalgorithm uses O(n/logck) samples for some constantc > 0 and polynomial space, then the query time of the data structure must be at leastk1 O(1)/loglogk, i.e., close to
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data.
On the Identifiability and Interpretability of Gaussian Process Models
Rather than specifying a model, the GP framework revolves around selecting an appropriate kernel, transforming the problem into one of parameter estimation.
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
Alpaca, created by applying SelectIT to the Alpaca-GPT4 dataset.
