Scalable Active Learning for Object Detection

Haußmann, Elmar; Fenzi, Michele; Chitta, Kashyap; Ivanecký, Ján; Xu, Hanson; Roy, Donna; Mittel, Akshita; Koumchatzky, Nicolas; Farabet, Clément; Álvarez, Jose M.

doi:10.1109/iv47402.2020.9304793

Cited by 90 publications

(61 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However beyond this number of classes, the approach is less appealing due to the increasing training cost. We note that in several practical settings, e.g., perception for driving assistance [82]- [85], the number of classes is often low, i.e., less than 10, (in order to avoid ambiguity and class imbalance, frequent drawbacks of high granularity datasets. For tasks that do not allow low number of classes, we indicate a few potential strategies to render OVNNI more feasible for such cases.…”

Section: E Limitations Of the Approach And Perspectivesmentioning

confidence: 99%

One Versus All for Deep Neural Network for Uncertainty (OVNNI) Quantification

Franchi¹,

Bursuc²,

Aldea³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Deep neural networks (DNNs) are powerful learning models yet their results are not always reliable. This drawback results from the fact that modern DNNs are usually overconfident, and consequently their epistemic uncertainty cannot be straightforwardly characterized. In this work, we propose a new technique to quantify the epistemic uncertainty of data easily. This method consists in mixing the predictions of an ensemble of DNNs trained to classify One class vs. All the other classes (OVA) with predictions from a standard DNN trained to perform All vs. All (AVA) classification. First of all, the adjustment provided by the AVA DNN to the score of the base classifiers allows for a more fine-grained inter-class separation. Moreover, the two types of classifiers enforce mutually their detection of out-of-distribution (OOD) samples, circumventing entirely the requirement of using such samples during training. The additional cost involved by the construction of the ensemble is offset by the ease of use of our proposed strategy and by its enhanced generalization potential, as it does not bind its performance in a given context to specific OOD datasets. The extensive experiments confirm the wide applicability of our approach, and our method achieves state of the art performance in quantifying OOD data across multiple datasets and architectures while requiring little hyper-parameter tuning.INDEX TERMS Uncertainty estimation, DNN ensembles, one vs all classification, all vs all classification.

show abstract

Section: E Limitations Of the Approach And Perspectivesmentioning

confidence: 99%

One Versus All for Deep Neural Network for Uncertainty (OVNNI) Quantification

Franchi¹,

Bursuc²,

Aldea³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In particular, for autonomous driving, remarkable results, particularly cone, pedestrian, and box detection for Advanced Driver Assistance Systems, were achieved through ensemble methods [42]. us, object detection for selfdriving cars presents an important challenge, which has been tackled using various ensemble techniques, including a multispectral ensemble detection pipeline, a scalable production system for active learning, and a soft-weightedaverage method for vehicle detection [43][44][45]. e work in this paper has been based on the algorithms proposed in [46,47] for ensembling detectors and employing voting strategies for object detection, which was able to deliver a 10% improvement from the base models.…”

Section: Ensemble Deep Learningmentioning

confidence: 99%

Lightweight Object Detection Ensemble Framework for Autonomous Vehicles in Challenging Weather Conditions

Walambe

Marathe

Kotecha

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The computer vision systems driving autonomous vehicles are judged by their ability to detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing this ability of a self-driving car to distinguish between the elements of its environment under adverse conditions is an important challenge in computer vision. For example, poor weather conditions like fog and rain lead to image corruption which can cause a drastic drop in object detection (OD) performance. The primary navigation of autonomous vehicles depends on the effectiveness of the image processing techniques applied to the data collected from various visual sensors. Therefore, it is essential to develop the capability to detect objects like vehicles and pedestrians under challenging conditions such as like unpleasant weather. Ensembling multiple baseline deep learning models under different voting strategies for object detection and utilizing data augmentation to boost the models’ performance is proposed to solve this problem. The data augmentation technique is particularly useful and works with limited training data for OD applications. Furthermore, using the baseline models significantly speeds up the OD process as compared to the custom models due to transfer learning. Therefore, the ensembling approach can be highly effective in resource-constrained devices deployed for autonomous vehicles in uncertain weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and were able to identify objects from the images captured in the adverse foggy and rainy weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and reached 32.75% mean average precision (mAP) and 52.56% average precision (AP) in detecting cars in the adverse fog and rain weather conditions present in the dataset. The effectiveness of multiple voting strategies for bounding box predictions on the dataset is also demonstrated. These strategies help increase the explainability of object detection in autonomous systems and improve the performance of the ensemble techniques over the baseline models.

show abstract

“…2a-b). In the next iteration q , instead of re-initializing with randomly selected examples, data collected from the previous iteration q −1 is used, constituting a build-up scheme implemented in many active learning methods [5, 10]. This process is repeated until the maximum number of rounds τ is reached.…”

Section: Supplementary Materialsmentioning

confidence: 99%

“…Among the four acquisition functions, variation ratios required an additional mode operation, contributing to increased training time. Based on these results, we suggest to set the member size between [3, 10] ∈𝕫 > 0 while increasing pathway subsampling size accordingly (e.g. 2000 for 10 members) to improve prediction outcomes and reduce both computational complexity (training and inference) and model size.…”

Section: Supplementary Materialsmentioning

confidence: 99%

“…These functions are overrepresented in labeled training data relative to more niche-defining or accessory metabolic functions and can result in training loss with decreased predictive performance. To address this problem, we developed leADS based on prior work in dataset subsampling [10]. leADS incorporates an ensemble of multi-label learners [32] to perform hard example mining [27], reducing the negative impact of training loss on pathway prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

leADS: improved metabolic pathway inference based on active dataset subsampling

Basher

Nallan

McLaughlin

et al. 2020

Preprint

View full text Add to dashboard Cite

Machine learning methods show great promise in predicting metabolic pathways at different levels of biological organization. However, several complications remain that can degrade prediction performance including inadequately labeled training data, missing feature information, and inherent imbalances in the distribution of enzymes and pathways within a dataset. This class imbalance problem is commonly encountered by the machine learning community when the proportion of instances over class labels within a dataset are uneven, resulting in poor predictive performance for underrepresented classes. Here, we present leADS, multi-label learning based on active dataset subsampling, that leverages the idea of subsampling points from a pool of data to reduce the negative impact of training loss due to class imbalance. Specifically, leADS performs an iterative process to: (i)-construct an acquisition model in an ensemble framework; (ii) select informative points using an appropriate acquisition function; and (iii) train on selected samples. Multiple base learners are implemented in parallel where each is assigned a portion of labeled training data to learn pathways. We benchmark leADS using a corpora of 10 experimental datasets manifesting diverse multi-label properties used in previous pathway prediction studies, including manually curated organismal genomes, synthetic microbial communities and low complexity microbial communities. Resulting performance metrics equaled or exceeded previously reported machine learning methods for both organismal and multi-organismal genomes while establishing an extensible framework for navigating class imbalances across diverse real world datasets.Availability and implementationThe software package, and installation instructions are published on github.com/leADSContactshallam@mail.ubc.ca

show abstract

Scalable Active Learning for Object Detection

Cited by 90 publications

References 6 publications

One Versus All for Deep Neural Network for Uncertainty (OVNNI) Quantification

One Versus All for Deep Neural Network for Uncertainty (OVNNI) Quantification

Lightweight Object Detection Ensemble Framework for Autonomous Vehicles in Challenging Weather Conditions

leADS: improved metabolic pathway inference based on active dataset subsampling

Contact Info

Product

Resources

About