Deep Learning for Plant Stress Phenotyping: Trends and Future Perspectives.

TL;DR: Out-of-distribution detection algorithms improve the robustness of insect classification models by preventing incorrect classification predictions on images that belong to non-insect and/or untrained insect classes.

TL;DR: A comprehensive analysis of stress detection and classification models for crop health assessment. Existing models are reviewed, focusing on performance, strengths, and limitations. Challenges and opportunities for future research are discussed.

TL;DR: In this paper , a multi-view fusion network was proposed to improve the performance of deep learning models for predicting dry matter, leaf dry matter and green matter yield of Guineagrass.

TL;DR: Sensor-based weed detection and GPS systems improve intra-row weeding precision, with robots distinguishing 99.7% of crop plants in dense areas, reducing manual work and herbicide use, and offering environmentally-friendly weed management options.

TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.