The iWildCam 2019 Challenge Dataset

Beery, Sara; Morris, Dan; Perona, Pietro

doi:10.48550/arxiv.1907.07617

Cited by 4 publications

(4 citation statements)

References 16 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this example, following Cloudera (2020), we adapt the iWildCam 2019 dataset (Beery et al, 2019) that contains wildlife images taken in the wild. The images are collected from different cameras, each at one of 143 locations.…”

Section: Natural Image Classificationmentioning

confidence: 99%

Optimization-based Causal Estimation from Heterogenous Environments

Yin¹,

Wang²,

Blei³

2021

Preprint

View full text Add to dashboard Cite

This paper presents a new optimization approach to causal estimation. Given data that contains covariates and an outcome, which covariates are causes of the outcome, and what is the strength of the causality? In classical machine learning (ML), the goal of optimization is to maximize predictive accuracy. However, some covariates might exhibit a non-causal association to the outcome. Such spurious associations provide predictive power for classical ML, but they prevent us from causally interpreting the result. This paper proposes CoCo, an optimization algorithm that bridges the gap between pure prediction and causal inference. CoCo leverages the recently-proposed idea of environments, datasets of covariates/response where the causal relationships remain invariant but where the distribution of the covariates changes from environment to environment. Given datasets from multiple environments-and ones that exhibit sufficient heterogeneity-CoCo maximizes an objective for which the only solution is the causal solution. We describe the theoretical foundations of this approach and demonstrate its effectiveness on simulated and real datasets. Compared to classical ML and existing methods, CoCo provides more accurate estimates of the causal model.

show abstract

Section: Natural Image Classificationmentioning

confidence: 99%

Optimization-based Causal Estimation from Heterogenous Environments

Yin¹,

Wang²,

Blei³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Fine-Grained Visual Categorization (FGVC): In many FGVC datasets [5,3,25,9], the number of categories is not extremely large, often less than 200. Recent largescale datasets [17,14,51] offer large numbers of categories with many images (e.g., 675,170 training images for 5089 categories [51]) with challenging long-tailed distributions.…”

Section: Related Workmentioning

confidence: 99%

ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill Identification

Usuyama¹,

Delgado²,

Hall³

et al. 2020

Preprint

View full text Add to dashboard Cite

Identifying prescription medications is a frequent task for patients and medical professionals; however, this is an error-prone task as many pills have similar appearances (e.g. white round pills), which increases the risk of medication errors. In this paper, we introduce ePillID, the largest public benchmark on pill image recognition, composed of 13k images representing 8184 appearance classes (two sides for 4092 pill types). For most of the appearance classes, there exists only one reference image, making it a challenging low-shot recognition setting. We present our experimental setup and evaluation results of various baseline models on the benchmark. The best baseline using a multi-head metric-learning approach with bilinear features performed remarkably well; however, our error analysis suggests that they still fail to distinguish particularly confusing classes. The code and data are available at https: //github.com/usuyama/ePillID-benchmark.

show abstract

“…The distribution of species in camera trap datasets is long-tailed [5,14,15,16,17,18], mimicking the distribution of species in the natural world. In [19], the Caltech Camera Traps (CCT) dataset [5,20], which contains a rare deer class, was augmented with synthetic deer images generated with 3D game engines to reduce the class imbalance and increase the pose and location diversity of the rare class samples.…”

Section: Introductionmentioning

confidence: 99%

Domain Adaptation for Rare Classes Augmented with Synthetic Samples

Das¹,

Robert-Jan²,

Lengyel³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain adaptation can be incorporated in a classifier to decrease the domain discrepancy between real and synthetic samples. While domain adaptation is generally applied on completely synthetic source domains and real target domains, we explore how domain adaptation can be applied when only a single rare class is augmented with simulated samples. As a testbed, we use a camera trap animal dataset with a rare deer class, which is augmented with synthetic deer samples. We adapt existing domain adaptation methods to two new methods for the single rare class setting: DeerDANN, based on the Domain-Adversarial Neural Network (DANN), and DeerCORAL, based on deep correlation alignment (Deep CORAL) architectures. Experiments show that DeerDANN has the highest improvement in deer classification accuracy of 24.0% versus 22.4% improvement of DeerCORAL when compared to the baseline. Further, both methods require fewer than 10k synthetic samples, as used by the baseline, to achieve these higher accuracies. DeerCORAL requires the least number of synthetic samples (2k deer), followed by DeerDANN (8k deer).

show abstract

The iWildCam 2019 Challenge Dataset

Cited by 4 publications

References 16 publications

Optimization-based Causal Estimation from Heterogenous Environments

Optimization-based Causal Estimation from Heterogenous Environments

ePillID Dataset: A Low-Shot Fine-Grained Benchmark for Pill Identification

Domain Adaptation for Rare Classes Augmented with Synthetic Samples

Contact Info

Product

Resources

About