Review of pixel-level remote sensing image fusion based on deep learning
Z Wang, Y Ma, Y Zhang - Information Fusion, 2023 - Elsevier
The booming development of remote sensing images in many visual tasks has led to an
increasing demand for obtaining images with more precise details. However, it is impractical …
increasing demand for obtaining images with more precise details. However, it is impractical …
Adaptive inference through early-exit networks: Design, challenges and directions
DNNs are becoming less and less over-parametrised due to recent advances in efficient
model design, through careful hand-crafted or NAS-based methods. Relying on the fact that …
model design, through careful hand-crafted or NAS-based methods. Relying on the fact that …
Feedback network for image super-resolution
Recent advances in image super-resolution (SR) explored the power of deep learning to
achieve a better reconstruction performance. However, the feedback mechanism, which …
achieve a better reconstruction performance. However, the feedback mechanism, which …
Deep back-projection networks for super-resolution
The feed-forward architectures of recently proposed deep super-resolution networks learn
representations of low-resolution inputs, and the non-linear map** from those to high …
representations of low-resolution inputs, and the non-linear map** from those to high …
Multi-scale dense networks for resource efficient image classification
In this paper we investigate image classification with computational resource limits at test
time. Two such settings are: 1. anytime classification, where the network's prediction for a …
time. Two such settings are: 1. anytime classification, where the network's prediction for a …
Latent embedding feedback and discriminative features for zero-shot classification
Zero-shot learning strives to classify unseen categories for which no data is available during
training. In the generalized variant, the test samples can further belong to seen or unseen …
training. In the generalized variant, the test samples can further belong to seen or unseen …
Dynamic task prioritization for multitask learning
We propose dynamic task prioritization for multitask learning. This allows a model to
dynamically prioritize difficult tasks during training, where difficulty is inversely proportional …
dynamically prioritize difficult tasks during training, where difficulty is inversely proportional …
Codeslam—learning a compact, optimisable representation for dense visual slam
The representation of geometry in real-time 3D perception systems continues to be a critical
research issue. Dense maps capture complete surface shape and can be augmented with …
research issue. Dense maps capture complete surface shape and can be augmented with …
Lightweight image super-resolution with expectation-maximization attention mechanism
X Zhu, K Guo, S Ren, B Hu, M Hu… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In recent years, with the rapid development of deep learning, super-resolution methods
based on convolutional neural networks (CNNs) have made great progress. However, the …
based on convolutional neural networks (CNNs) have made great progress. However, the …
Context reasoning attention network for image super-resolution
Deep convolutional neural networks (CNNs) are achieving great successes for image super-
resolution (SR), where global context is crucial for accurate restoration. However, the basic …
resolution (SR), where global context is crucial for accurate restoration. However, the basic …