An Active Learning Formulation for Instance Selection with Applications to Object Detection

Sung, Kah-Kay; Niyogi, Partha

doi:10.1007/978-1-4757-3359-4_20

Cited by 6 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This local patch based training has several benefits; it 1) reduces the training time by 50× 2 , 2) helps generalization across different parts of the image as the model is unable to rely on global statistics of ball positions, 3) offers a more fine-grained selection of training data for non-trivial cases e.g. when another ball is still moving in the scene, and similarly 4) allows for hard negative mining [89] on sequences where it is known for no ball to exist in play.…”

Section: C) Training the Detector Modelmentioning

confidence: 99%

Robotic Table Tennis: A Case Study into a High Speed Learning System

D'Ambrosio,

Jaitly,

Sindhwani

et al. 2023

Robotics: Science and Systems XIX

View full text Add to dashboard Cite

Section: C) Training the Detector Modelmentioning

confidence: 99%

Robotic Table Tennis: A Case Study into a High Speed Learning System

D'Ambrosio,

Jaitly,

Sindhwani

et al. 2023

Robotics: Science and Systems XIX

View full text Add to dashboard Cite

“…Here, we developed an active and machine learning-based approach to design gene expression constructs for metabolic engineering-ActiveOpt-that overcomes many of the aforementioned drawbacks. Although this is the first reported study that uses active learning-in metabolic engineering, active learning has been previously used in a wide range of other applications (24), (25), (26), (27), (28), (29), (30). ActiveOpt integrates computational and experimental efforts to improve metabolic engineering objectives using substantially fewer and simpler experiments (e.g., measuring biochemical yield or productivity) than many state-of-theart approaches.…”

Section: Introductionmentioning

confidence: 99%

Active and machine learning-based approaches to rapidly enhance microbial chemical production

Kumar

Adamczyk

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

In order to make renewable fuels and chemicals from microbes, new methods are required to engineer microbes more intelligently. Computational approaches, to engineer strains for enhanced chemical production typically rely on detailed mechanistic models (e.g., kinetic/stoichiometric models of metabolism) requiring many experimental datasets for their parameterization, while experimental methods may require screening large mutant libraries to explore the design space for the few mutants with desired behaviors. To address these limitations, we developed an active and machine learning approach (ActiveOpt) to intelligently guide experiments to arrive at an optimal phenotype with minimal measured datasets. ActiveOpt was applied to two separate case studies to evaluate its potential to increase valine yields and neurosporene productivity in Escherichia coli. In both the cases, ActiveOpt identified the best performing strain in fewer experiments than the case studies used. This work demonstrates that machine and active learning approaches have the potential to greatly facilitate metabolic engineering efforts to rapidly achieve its objectives.

show abstract

“…Dating back to the 1960s [19], computer-assisted face recognition has progressed over the past decades from handcrafted feature representation methods [20] (e.g. Eigenfaces [21], DBSCAN [22], Viola-Jones [23], HoG [24]) to deep learning models.…”

mentioning

confidence: 99%

A Comprehensive Survey on Backdoor Attacks and Their Defenses in Face Recognition Systems

Roux,

Bourbao,

Teglia

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Deep learning has significantly transformed face recognition, enabling the deployment of large-scale, state-of-the-art solutions worldwide. However, the widespread adoption of deep neural networks (DNNs) and the rise of Machine Learning as a Service emphasize the need for secure DNNs. This paper revisits the face recognition threat model in the context of DNN ubiquity and the common practice of outsourcing their training and hosting to third-parties. Here, we identify backdoor attacks as a significant threat to modern DNN-based face recognition systems (FRS). Backdoor attacks involve an attacker manipulating a DNN's training or deployment, injecting it with a stealthy and malicious behavior. Once the DNN has entered its inference stage, the attacker may activate the backdoor and compromise the DNN's intended functionality. Given the critical nature of this threat to DNN-based FRS, our paper comprehensively surveys the literature of backdoor attacks and defenses previously demonstrated on FRS DNNs. As a last point, we highlight potential vulnerabilities and unexplored areas in FRS security.

show abstract

An Active Learning Formulation for Instance Selection with Applications to Object Detection

Cited by 6 publications

References 4 publications

Robotic Table Tennis: A Case Study into a High Speed Learning System

Robotic Table Tennis: A Case Study into a High Speed Learning System

Active and machine learning-based approaches to rapidly enhance microbial chemical production

A Comprehensive Survey on Backdoor Attacks and Their Defenses in Face Recognition Systems

Contact Info

Product

Resources

About