vSketchDLC: A Sketch on Distributed Deep Learning Communication via Fine-grained Tracing Visualization

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

Download Full-text

Representation Learning for Fine-Grained Change Detection

Sensors ◽

10.3390/s21134486 ◽

2021 ◽

Vol 21 (13) ◽

pp. 4486

Author(s):

Niall O’Mahony ◽

Sean Campbell ◽

Lenka Krpalkova ◽

Anderson Carvalho ◽

Joseph Walsh ◽

...

Keyword(s):

Deep Learning ◽

Change Detection ◽

Model Calibration ◽

State Of The Art ◽

Representation Learning ◽

Machine Intelligence ◽

The State ◽

Sensor Data ◽

Fine Grained ◽

Learning Techniques

Fine-grained change detection in sensor data is very challenging for artificial intelligence though it is critically important in practice. It is the process of identifying differences in the state of an object or phenomenon where the differences are class-specific and are difficult to generalise. As a result, many recent technologies that leverage big data and deep learning struggle with this task. This review focuses on the state-of-the-art methods, applications, and challenges of representation learning for fine-grained change detection. Our research focuses on methods of harnessing the latent metric space of representation learning techniques as an interim output for hybrid human-machine intelligence. We review methods for transforming and projecting embedding space such that significant changes can be communicated more effectively and a more comprehensive interpretation of underlying relationships in sensor data is facilitated. We conduct this research in our work towards developing a method for aligning the axes of latent embedding space with meaningful real-world metrics so that the reasoning behind the detection of change in relation to past observations may be revealed and adjusted. This is an important topic in many fields concerned with producing more meaningful and explainable outputs from deep learning and also for providing means for knowledge injection and model calibration in order to maintain user confidence.

Download Full-text

Deep Learning-Based Object Detection Improvement for Fine-Grained Birds

IEEE Access ◽

10.1109/access.2021.3076429 ◽

2021 ◽

pp. 1-1

Author(s):

Kuihe Yang ◽

Ziying Song

Keyword(s):

Deep Learning ◽

Object Detection ◽

Fine Grained

Download Full-text

VulDeeLocator: A Deep Learning-based Fine-grained Vulnerability Detector

IEEE Transactions on Dependable and Secure Computing ◽

10.1109/tdsc.2021.3076142 ◽

2021 ◽

pp. 1-1

Author(s):

Zhen Li ◽

Deqing Zou ◽

Shouhuai Xu ◽

Zhaoxuan Chen ◽

Yawei Zhu ◽

...

Keyword(s):

Deep Learning ◽

Fine Grained

Download Full-text

Errata for "Cerebro: a data system for optimized deep learning model selection"

Proceedings of the VLDB Endowment ◽

10.14778/3447689.3447691 ◽

2021 ◽

Vol 14 (6) ◽

pp. 863-863

Author(s):

Supun Nakandala ◽

Yuhao Zhang ◽

Arun Kumar

Keyword(s):

Deep Learning ◽

Model Selection ◽

Learning Model ◽

Communication Cost ◽

Data System ◽

Training Method ◽

Fine Grained ◽

Correct Communication ◽

Deep Learning Model

We discovered that there was an inconsistency in the communication cost formulation for the decentralized fine-grained training method in Table 2 of our paper [1]. We used Horovod as the archetype for decentralized fine-grained approaches, and its correct communication cost is higher than what we had reported. So, we amend the communication cost of decentralized fine-grained to [EQUATION]

Download Full-text

A Novel Deep Learning Approach of Convolutional Neural Network and Random Forest Classifier for Fine-grained Sentiment Classification

International Journal on Electrical Engineering and Informatics ◽

10.15676/ijeei.2021.13.2.13 ◽

2021 ◽

Vol 13 (2) ◽

pp. 465-476

Author(s):

Siji George C. G. ◽

◽

B Sumathi ◽

Keyword(s):

Neural Network ◽

Deep Learning ◽

Random Forest ◽

Convolutional Neural Network ◽

Random Forest Classifier ◽

Sentiment Classification ◽

Learning Approach ◽

Fine Grained

Download Full-text

Senti-BAS: A BERT-based model with sentiment computing for happiness research (Preprint)

10.2196/preprints.27914 ◽

2021 ◽

Author(s):

Zeyuan Zeng ◽

Yijia Zhang ◽

Liang Yang ◽

Hongfei Lin

Keyword(s):

Deep Learning ◽

Natural Language Processing ◽

Language Processing ◽

High Accuracy ◽

Language Models ◽

Fine Grained ◽

Label Information ◽

Common Criterion ◽

Text Content ◽

Sentiment Computing

BACKGROUND Happiness becomes a rising topic that we all care about recently. It can be described in various forms. For the text content, it is an interesting subject that we can do research on happiness by utilizing natural language processing (NLP) methods. OBJECTIVE As an abstract and complicated emotion, there is no common criterion to measure and describe happiness. Therefore, researchers are creating different models to study and measure happiness. METHODS In this paper, we present a deep-learning based model called Senti-BAS (BERT embedded Bi-LSTM with self-Attention mechanism along with the Sentiment computing). RESULTS Given a sentence that describes how a person felt happiness recently, the model can classify the happiness scenario in the sentence with two topics: was it controlled by the author (label ‘agency’), and was it involving other people (label ‘social’). Besides language models, we employ the label information through sentiment computing based on lexicon. CONCLUSIONS The model performs with a high accuracy on both ‘agency’ and ‘social’ labels, and we also make comparisons with several popular embedding models like Elmo, GPT. Depending on our work, we can study the happiness at a more fine-grained level.

Download Full-text

Fine-Grained Recognition: Accounting for Subtle Differences between Similar Classes

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6882 ◽

2020 ◽

Vol 34 (07) ◽

pp. 12047-12054

Author(s):

Guolei Sun ◽

Hisham Cholakkal ◽

Salman Khan ◽

Fahad Khan ◽

Ling Shao

Keyword(s):

Deep Learning ◽

Loss Function ◽

Recognition Task ◽

Data Driven ◽

Gradient Boosting ◽

Correct Classification ◽

Experimental Setting ◽

Fine Grained ◽

Feature Representations ◽

Salient Features

The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other. We note that existing methods implicitly address this requirement and leave it to a data-driven pipeline to figure out what makes a subordinate class different from the others. This results in two major limitations: First, the network focuses on the most obvious distinctions between classes and overlooks more subtle inter-class variations. Second, the chance of misclassifying a given sample in any of the negative classes is considered equal, while in fact, confusions generally occur among only the most similar classes. Here, we propose to explicitly force the network to find the subtle differences among closely related classes. In this pursuit, we introduce two key novelties that can be easily plugged into existing end-to-end deep learning pipelines. On one hand, we introduce “diversification block” which masks the most salient features for an input to force the network to use more subtle cues for its correct classification. Concurrently, we introduce a “gradient-boosting” loss function that focuses only on the confusing classes for each sample and therefore moves swiftly along the direction on the loss surface that seeks to resolve these ambiguities. The synergy between these two blocks helps the network to learn more effective feature representations. Comprehensive experiments are performed on five challenging datasets. Our approach outperforms existing methods using similar experimental setting on all five datasets.

Download Full-text