Search

Total foliage dry mass and leaf area at the canopy hierarchical level of needle, shoot, branch and crown were measured in 48 trees harvested from a 14-year-old loblolly pine (Pinus taeda L.) plantation, six growing seasons after thinning and fertilization treatments.In the unthinned treatment, upper crown needles were heavier and had more leaf area than lower crown needles. Branch- and crown-level leaf area of the thinned trees increased 91 and 109%, respectively, and whole-crown foliage biomass doubled. The increased crown leaf area was a result of more live branches and foliated shoots and larger branch sizes in the thinned treatment. Branch leaf area increased with increasing crown depth from the top to the mid-crown and decreased towards the base of the crown. Thinning stimulated foliage growth chiefly in the lower crown. At the same crown depth in the lower crown, branch leaf area was greater in the thinned treatment than in the unthinned treatment. Maximum leaf area per branch was located nearly 3–4 m below the top of the crown in the unthinned treatment and 4–5 m in the thinned treatment. Leaf area of the thinned-treatment trees increased 70% in the upper crown and 130% in the lower crown. Fertilization enhanced needle size and leaf area in the upper crown, but had no effect on leaf area and other variables at the shoot, branch and crown level. We conclude that the thinning-induced increase in light penetration within the canopy leads to increased branch size and crown leaf area. However, the branch and crown attributes have little response to fertilization and its interaction with thinning. [Copyright &y& Elsevier]

The goal of this work is to automatically collect a large number of highly relevant natural images from Internet for given queries. A novel automatic image dataset construction framework is proposed by employing multiple query expansions. In specific, the given queries are first expanded by searching in the Google Books Ngrams Corpora to obtain a richer semantic descriptions, from which the visually non-salient and less relevant expansions are then filtered. After retrieving images from the Internet with filtered expansions, we further filter noisy images by clustering and progressively Convolutional Neural Networks (CNN) based methods. To evaluate the performance of our proposed method for image dataset construction, we build an image dataset with 10 categories. We then run object detections on our image dataset with three other image datasets which were constructed by weak supervised, web supervised and full supervised learning, the experimental results indicated the effectiveness of our method is superior to weak supervised and web supervised state-of-the-art methods. In addition, we do a cross-dataset classification to evaluate the performance of our dataset with two publically available manual labelled dataset STL-10 and CIFAR-10. [ABSTRACT FROM AUTHOR]

• Mitigate the harmful effects of label noise and capture discriminative feature representations simultaneously • Decouple the joint optimization to promote the generalization performance • Refurbish training procedure with accumulated predictions and consistency • Achieves state-of-the-art performance for the web-supervised fine-grained recognition task Due to DNNs' memorization effect, label noise lessens the performance of the web-supervised fine-grained visual categorization task. Previous literature primarily relies on small-loss instances for subsequent training. The current state-of-the-art approach JoCoR additionally employs explicit consistency constraints to make clean samples more confident. However, a joint loss designed for both sample selection criteria and parameter updating is not competent for training a robust model in the presence of web noise. Especially, false positives are assigned with larger weights, causing the model to pay more attention to misclassified noisy images. Besides, leveraging weight decay to forget discarded noisy instances is too slow and implicit to take effect. Therefore, we propose a simple yet effective approach named MS-DeJOR (M ulti- S cale training with De coupled J oint O ptimization and R efurbishment). In contrast to JoCoR, we decouple sample selection from training procedure to handle the above problems. Specifically, a negative entropy term is applied to prevent false positives from being overemphasized. The model can explicitly forget those samples identified as noise by imposing such a regularization term on all training data. Furthermore, we use accumulated predictions to refurbish the noisy labels and re-weight training images to boost the model performance. A multi-scale feature enhancement module is adopted to extract discriminative and subtle feature representations. Extensive experiments show that MS-DeJOR yields state-of-the-art performances on three web-supervised fine-grained datasets, demonstrating the effectiveness of our approach. The data and source code have been available at https://github.com/msdejor/MS-DeJOR. [ABSTRACT FROM AUTHOR]

• Adapt to dynamic changes in search results and carry out visual disambiguation. • A saliency-guided deep MIL network to remove outliers and learn visual disambiguation. • Identify appropriate visual senses for sense-specific image collection. • Be used as a pre-step before learning from the web for improving the performance. Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits the performance of current webly supervised models is the problem of visual polysemy. In this work, we present a novel framework that resolves visual polysemy by dynamically matching candidate text queries with retrieved images. Specifically, our proposed framework includes three major steps: we first discover and then dynamically select the text queries according to the keyword-based image search results, we employ the proposed saliency-guided deep multi-instance learning (MIL) network to remove outliers and learn classification models for visual disambiguation. Compared to existing methods, our proposed approach can figure out the right visual senses, adapt to dynamic changes in the search results, remove outliers, and jointly learn the classification models. Extensive experiments and ablation studies on CMU-Poly-30 and MIT-ISD datasets demonstrate the effectiveness of our proposed approach. [ABSTRACT FROM AUTHOR]