Hyongsuk Kim

Mingle Xu, Jaehwan Lee, Sook Yoon et al.

Semantic image synthesis (SIS) aims to produce photorealistic images aligning to given conditional semantic layout and has witnessed a significant improvement in recent years. Although the diversity in image-level has been discussed heavily, class-level mode collapse widely exists in current algorithms. Therefore, we declare a new requirement for SIS to achieve more photorealistic images, variation-aware, which consists of inter- and intra-class variation. The inter-class variation is the diversity between different semantic classes while the intra-class variation stresses the diversity inside one class. Through analysis, we find that current algorithms elusively embrace the inter-class variation but the intra-class variation is still not enough. Further, we introduce two simple methods to achieve variation-aware semantic image synthesis (VASIS) with a higher intra-class variation, semantic noise and position code. We combine our method with several state-of-the-art algorithms and the experimental result shows that our models generate more natural images and achieves slightly better FIDs and/or mIoUs than the counterparts. Our codes and models will be publicly available.

Mingle Xu, Hyongsuk Kim, Jucheng Yang et al.

Recent advancements in deep learning have brought significant improvements to plant disease recognition. However, achieving satisfactory performance often requires high-quality training datasets, which are challenging and expensive to collect. Consequently, the practical application of current deep learning-based methods in real-world scenarios is hindered by the scarcity of high-quality datasets. In this paper, we argue that embracing poor datasets is viable and aim to explicitly define the challenges associated with using these datasets. To delve into this topic, we analyze the characteristics of high-quality datasets, namely large-scale images and desired annotation, and contrast them with the \emph{limited} and \emph{imperfect} nature of poor datasets. Challenges arise when the training datasets deviate from these characteristics. To provide a comprehensive understanding, we propose a novel and informative taxonomy that categorizes these challenges. Furthermore, we offer a brief overview of existing studies and approaches that address these challenges. We believe that our paper sheds light on the importance of embracing poor datasets, enhances the understanding of the associated challenges, and contributes to the ambitious objective of deploying deep learning in real-world applications. To facilitate the progress, we finally describe several outstanding questions and point out potential future directions. Although our primary focus is on plant disease recognition, we emphasize that the principles of embracing and analyzing poor datasets are applicable to a wider range of domains, including agriculture.

Talha Ilyas, Dewa Made Sri Arsa, Khubaib Ahmad et al.

The growing demand for precision agriculture necessitates efficient and accurate crop-weed recognition and classification systems. Current datasets often lack the sample size, diversity, and hierarchical structure needed to develop robust deep learning models for discriminating crops and weeds in agricultural fields. Moreover, the similar external structure and phenomics of crops and weeds complicate recognition tasks. To address these issues, we present the CWD30 dataset, a large-scale, diverse, holistic, and hierarchical dataset tailored for crop-weed recognition tasks in precision agriculture. CWD30 comprises over 219,770 high-resolution images of 20 weed species and 10 crop species, encompassing various growth stages, multiple viewing angles, and environmental conditions. The images were collected from diverse agricultural fields across different geographic locations and seasons, ensuring a representative dataset. The dataset's hierarchical taxonomy enables fine-grained classification and facilitates the development of more accurate, robust, and generalizable deep learning models. We conduct extensive baseline experiments to validate the efficacy of the CWD30 dataset. Our experiments reveal that the dataset poses significant challenges due to intra-class variations, inter-class similarities, and data imbalance. Additionally, we demonstrate that minor training modifications like using CWD30 pretrained backbones can significantly enhance model performance and reduce convergence time, saving training resources on several downstream tasks. These challenges provide valuable insights and opportunities for future research in crop-weed recognition. We believe that the CWD30 dataset will serve as a benchmark for evaluating crop-weed recognition algorithms, promoting advancements in precision agriculture, and fostering collaboration among researchers in the field.

Mohammad Ibrahim Sarker, Hyongsuk Kim, Denis Tarasov et al.

This paper presents results of applying Inception v4 deep convolutional neural network to ICIAR-2018 Breast Cancer Classification Grand Challenge, part a. The Challenge task is to classify breast cancer biopsy results, presented in form of hematoxylin and eosin stained images. Breast cancer classification is of primary interest to the medical practitioners and thus binary classification of breast cancer images have been under investigation by many researchers, but multi-class categorization of histology breast images have been challenging due to the subtle differences among the categories. In this work extensive data augmentation is conducted to reduce overfitting and effectiveness of committee of several Inception v4 networks is studied. We report 89% accuracy on 4 class classification task and 93.7% on carcinoma/non-carcinoma two class classification task using our test set of 80 images.

Mohammad Ibrahim Sarker, Heechan Yang, Hyongsuk Kim

The field of machine learning has become an increasingly budding area of research as more efficient methods are needed in the quest to handle more complex image detection challenges. To solve the problems of agriculture is more and more important because food is the fundamental of life. However, the detection accuracy in recent corn field systems are still far away from the demands in practice due to a number of different weeds. This paper presents a model to handle the problem of corn leaf detection in given digital images collected from farm field. Based on results of experiments conducted with several state-of-the-art models adopted by CNN, a region-based method has been proposed as a faster and more accurate method of corn leaf detection. Being motivated with such unique attributes of ResNet, we combine it with region based network (such as faster rcnn), which is able to automatically detect corn leaf in heavy weeds occlusion. The method is evaluated on the dataset from farm and we make an annotation ourselves. Our proposed method achieves significantly outperform in corn detection system.

Mohammad Ibrahim Sarker, Zubaer Ibna Mannan, Hyongsuk Kim

Random weight change (RWC) algorithm is extremely component and robust for the hardware implementation of neural networks. RWC and Genetic algorithm (GA) are well known methodologies used for optimizing and learning the neural network (NN). Individually, each of these two algorithms has its strength and weakness along with separate objectives. However, recently, researchers combine these two algorithms for better learning and optimization of NN. In this paper, we proposed a methodology by combining the RWC and GA, namely Genetic Random Weight Change (GRWC), as well as demonstrate a seminal way to reduce the complexity of the neural network by removing weak weights of GRWC. In contrast to RWC and GA, GRWC contains an effective optimization procedure which is worthy at exploring a large and complex space in intellectual strategies influenced by the GA/RWC synergy. The learning behavior of the proposed algorithm was tested on MNIST dataset and it was able to prove its performance.

Mohammad Ibraim Sarker, Yali Nie, Hong Yongki et al.

A new method to improve the performance of Random weight change (RWC) algorithm based on a simple genetic algorithm, namely, Genetic random weight change (GRWC) is proposed. It is to find the optimal values of global minima via learning. In contrast to Random Weight Change (RWC), GRWC contains an effective optimization procedure which are good at exploring a large and complex space in an intellectual strategies influenced by the GA/RWC synergy. By implementing our simple GA in RWC we achieve an astounding accuracy of finding global minima.

Mohammad Ibrahim Sarker, Hyongsuk Kim

Machine learning has become a major field of research in order to handle more and more complex image detection problems. Among the existing state-of-the-art CNN models, in this paper a region-based, fully convolutional network, for fast and accurate object detection has been proposed based on the experimental results. Among the region based networks, ResNet is regarded as the most recent CNN architecture which has obtained the best results at ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) in 2015. Deep residual networks (ResNets) can make the training process faster and attain more accuracy compared to their equivalent conventional neural networks. Being motivated with such unique attributes of ResNet, this paper evaluates the performance of fine-tuned ResNet for object classification of our weeds dataset. The dataset of farm land weeds detection is insufficient to train such deep CNN models. To overcome this shortcoming, we perform dropout techniques along with deep residual network for reducing over-fitting problem as well as applying data augmentation with the proposed ResNet to achieve a significant outperforming result from our weeds dataset. We achieved better object detection performance with Region-based Fully Convolutional Networks (R-FCN) technique which is latched with our proposed ResNet-101.