RESUMEN
Training deep learning models typically requires a huge amount of labeled data which is expensive to acquire, especially in dense prediction tasks such as semantic segmentation. Moreover, plant phenotyping datasets pose additional challenges of heavy occlusion and varied lighting conditions which makes annotations more time-consuming to obtain. Active learning helps in reducing the annotation cost by selecting samples for labeling which are most informative to the model, thus improving model performance with fewer annotations. Active learning for semantic segmentation has been well studied on datasets such as PASCAL VOC and Cityscapes. However, its effectiveness on plant datasets has not received much importance. To bridge this gap, we empirically study and benchmark the effectiveness of four uncertainty-based active learning strategies on three natural plant organ segmentation datasets. We also study their behaviour in response to variations in training configurations in terms of augmentations used, the scale of training images, active learning batch sizes, and train-validation set splits.
RESUMEN
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few efforts have been reported to address this limitation, all of which apply variants of knowledge distillation to avoid catastrophic forgetting. We note that although distillation helps to retain previous learning, it obstructs fast adaptability to new tasks, which is a critical requirement for incremental learning. In this pursuit, we propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. This ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection. We evaluate our approach on a variety of incremental learning settings defined on PASCAL-VOC and MS COCO datasets, where our approach performs favourably well against state-of-the-art methods. Code and trained models: https://github.com/JosephKJ/iOD.
RESUMEN
We present DANTE, a novel method for training neural networks using the alternating minimization principle. DANTE provides an alternate perspective to traditional gradient-based backpropagation techniques commonly used to train deep networks. It utilizes an adaptation of quasi-convexity to cast training a neural network as a bi-quasi-convex optimization problem. We show that for neural network configurations with both differentiable (e.g. sigmoid) and non-differentiable (e.g. ReLU) activation functions, we can perform the alternations effectively in this formulation. DANTE can also be extended to networks with multiple hidden layers. In experiments on standard datasets, neural networks trained using the proposed method were found to be promising and competitive to traditional backpropagation techniques, both in terms of quality of the solution, as well as training speed.
Asunto(s)
Redes Neurales de la Computación , Programas InformáticosRESUMEN
BACKGROUND: Panicle density of cereal crops such as wheat and sorghum is one of the main components for plant breeders and agronomists in understanding the yield of their crops. To phenotype the panicle density effectively, researchers agree there is a significant need for computer vision-based object detection techniques. Especially in recent times, research in deep learning-based object detection shows promising results in various agricultural studies. However, training such systems usually requires a lot of bounding-box labeled data. Since crops vary by both environmental and genetic conditions, acquisition of huge amount of labeled image datasets for each crop is expensive and time-consuming. Thus, to catalyze the widespread usage of automatic object detection for crop phenotyping, a cost-effective method to develop such automated systems is essential. RESULTS: We propose a point supervision based active learning approach for panicle detection in cereal crops. In our approach, the model constantly interacts with a human annotator by iteratively querying the labels for only the most informative images, as opposed to all images in a dataset. Our query method is specifically designed for cereal crops which usually tend to have panicles with low variance in appearance. Our method reduces labeling costs by intelligently leveraging low-cost weak labels (object centers) for picking the most informative images for which strong labels (bounding boxes) are required. We show promising results on two publicly available cereal crop datasets-Sorghum and Wheat. On Sorghum, 6 variants of our proposed method outperform the best baseline method with more than 55% savings in labeling time. Similarly, on Wheat, 3 variants of our proposed methods outperform the best baseline method with more than 50% of savings in labeling time. CONCLUSION: We proposed a cost effective method to train reliable panicle detectors for cereal crops. A low cost panicle detection method for cereal crops is highly beneficial to both breeders and agronomists. Plant breeders can obtain quick crop yield estimates to make important crop management decisions. Similarly, obtaining real time visual crop analysis is valuable for researchers to analyze the crop's response to various experimental conditions.
RESUMEN
BACKGROUND: Accurate estimation of heading date of paddy rice greatly helps the breeders to understand the adaptability of different crop varieties in a given location. The heading date also plays a vital role in determining grain yield for research experiments. Visual examination of the crop is laborious and time consuming. Therefore, quick and precise estimation of heading date of paddy rice is highly essential. RESULTS: In this work, we propose a simple pipeline to detect regions containing flowering panicles from ground level RGB images of paddy rice. Given a fixed region size for an image, the number of regions containing flowering panicles is directly proportional to the number of flowering panicles present. Consequently, we use the flowering panicle region counts to estimate the heading date of the crop. The method is based on image classification using Convolutional Neural Networks. We evaluated the performance of our algorithm on five time series image sequences of three different varieties of rice crops. When compared to the previous work on this dataset, the accuracy and general versatility of the method has been improved and heading date has been estimated with a mean absolute error of less than 1 day. CONCLUSION: An efficient heading date estimation method has been described for rice crops using time series RGB images of crop under natural field conditions. This study demonstrated that our method can reliably be used as a replacement of manual observation to detect the heading date of rice crops.