Understanding Deep Learning Techniques for Image Segmentation

Ghosh, Swarnendu; Das, Nibaran; Das, Ishita; Maulik, Ujjwal

doi:10.1145/3329784

Cited by 279 publications

(114 citation statements)

References 202 publications

(205 reference statements)

Supporting

Mentioning

107

Contrasting

Unclassified

Order By: Relevance

“…There have been many studies addressing the task of semantic image segmentation with deep learning techniques [2,39]. Fully Convolutional Network (FCN) [40] was first proposed for effective pixel-level classification.…”

Section: Semantic Image Segmentationmentioning

confidence: 99%

Deep multimodal fusion for semantic image segmentation: A survey

Zhang

Sidibé

Morel

et al. 2021

Image and Vision Computing

120

View full text Add to dashboard Cite

Recent advances in deep learning have shown excellent performance in various scene understanding tasks. However, in some complex environments or under challenging conditions, it is necessary to employ multiple modalities that provide complementary information on the same scene. A variety of studies have demonstrated that deep multimodal fusion for semantic image segmentation achieves significant performance improvement. These fusion approaches take the benefits of multiple information sources and generate an optimal joint prediction automatically. This paper describes the essential background concepts of deep multimodal fusion and the relevant applications in computer vision. In particular, we provide a systematic survey of multimodal fusion methodologies, multimodal segmentation datasets, and quantitative evaluations on the benchmark datasets. Existing fusion methods are summarized according to a common taxonomy: early fusion, late fusion, and hybrid fusion. Based on their performance, we analyze the strengths and weaknesses of different fusion strategies. Current challenges and design choices are discussed, aiming to provide the reader with a comprehensive and heuristic view of deep multimodal image segmentation.

show abstract

Section: Semantic Image Segmentationmentioning

confidence: 99%

Deep multimodal fusion for semantic image segmentation: A survey

Zhang

Sidibé

Morel

et al. 2021

Image and Vision Computing

120

View full text Add to dashboard Cite

show abstract

“…Artificial neural networks have recently gained a lot of attention due to the application of deep learning techniques allowing for obtainmentn of excellent results in different machine learning tasks [35]. The cost of obtaining such results is the increasing complexity of the underlying model.…”

Section: Related Workmentioning

confidence: 99%

An Agave Counting Methodology Based on Mathematical Morphology and Images Acquired through Unmanned Aerial Vehicles

Calvario

Alarcón

Dalmau

et al. 2020

Sensors

View full text Add to dashboard Cite

Blue agave is an important commercial crop in Mexico, and it is the main source of the traditional mexican beverage known as tequila. The variety of blue agave crop known as Tequilana Weber is a crucial element for tequila agribusiness and the agricultural economy in Mexico. The number of agave plants in the field is one of the main parameters for estimating production of tequila. In this manuscript, we describe a mathematical morphology-based algorithm that addresses the agave automatic counting task. The proposed methodology was applied to a set of real images collected using an Unmanned Aerial Vehicle equipped with a digital Red-Green-Blue (RGB) camera. The number of plants automatically identified in the collected images was compared to the number of plants counted by hand. Accuracy of the proposed algorithm depended on the size heterogeneity of plants in the field and illumination. Accuracy ranged from 0.8309 to 0.9806, and performance of the proposed algorithm was satisfactory.

show abstract

“…The CNN has been outstandingly utilized for the data analysis of remote sensing domains, in particular, land cover classification or segmentation of agriculture or forest districts [10,12,[22][23][24][25][26]. It has rapidly become a successful method for accelerating the process of computer vision tasks, e.g., image classification, object detection, or semantic segmentation with high precision results [4,[27][28][29][30][31][32][33] and is a fast-growing area.…”

Section: Related Workmentioning

confidence: 99%

Semantic Labeling in Remote Sensing Corpora Using Feature Fusion-Based Enhanced Global Convolutional Network with High-Resolution Representations and Depthwise Atrous Convolution

et al. 2020

View full text Add to dashboard Cite

One of the fundamental tasks in remote sensing is the semantic segmentation on the aerial and satellite images. It plays a vital role in applications, such as agriculture planning, map updates, route optimization, and navigation. The state-of-the-art model is the Enhanced Global Convolutional Network (GCN152-TL-A) from our previous work. It composes two main components: (i) the backbone network to extract features and ( i i ) the segmentation network to annotate labels. However, the accuracy can be further improved, since the deep learning network is not designed for recovering low-level features (e.g., river, low vegetation). In this paper, we aim to improve the semantic segmentation network in three aspects, designed explicitly for the remotely sensed domain. First, we propose to employ a modern backbone network called “High-Resolution Representation (HR)” to extract features with higher quality. It repeatedly fuses the representations generated by the high-to-low subnetworks with the restoration of the low-resolution representations to the same depth and level. Second, “Feature Fusion (FF)” is added to our network to capture low-level features (e.g., lines, dots, or gradient orientation). It fuses between the features from the backbone and the segmentation models, which helps to prevent the loss of these low-level features. Finally, “Depthwise Atrous Convolution (DA)” is introduced to refine the extracted features by using four multi-resolution layers in collaboration with a dilated convolution strategy. The experiment was conducted on three data sets: two private corpora from Landsat-8 satellite and one public benchmark from the “ISPRS Vaihingen” challenge. There are two baseline models: the Deep Encoder-Decoder Network (DCED) and our previous model. The results show that the proposed model significantly outperforms all baselines. It is the winner in all data sets and exceeds more than 90% of F 1 : 0.9114, 0.9362, and 0.9111 in two Landsat-8 and ISPRS Vaihingen data sets, respectively. Furthermore, it achieves an accuracy beyond 90% on almost all classes.

show abstract

Understanding Deep Learning Techniques for Image Segmentation

Cited by 279 publications

References 202 publications

Deep multimodal fusion for semantic image segmentation: A survey

Deep multimodal fusion for semantic image segmentation: A survey

An Agave Counting Methodology Based on Mathematical Morphology and Images Acquired through Unmanned Aerial Vehicles

Semantic Labeling in Remote Sensing Corpora Using Feature Fusion-Based Enhanced Global Convolutional Network with High-Resolution Representations and Depthwise Atrous Convolution

Contact Info

Product

Resources

About