A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision

Abstract

Existing model evaluation tools mainly focus on evaluating classification models, leaving a gap in evaluating more complex models, such as object detection. In this paper, we develop an open-source visual analysis tool, Uni-Evaluator, to support a unified model evaluation for classification, object detection, and instance segmentation in computer vision. The key idea behind our method is to formulate both discrete and continuous predictions in different tasks as unified probability distributions. Based on these distributions, we develop 1) a matrix-based visualization to provide an overview of model performance; 2) a table visualization to identify the problematic data subsets where the model performs poorly; 3) a grid visualization to display the samples of interest. These visualizations work together to facilitate the model evaluation from a global overview to individual samples. Two case studies demonstrate the effectiveness of Uni-Evaluator in evaluating model performance and making informed improvements.

Emerging Technologies for Automation in Environmental Sensing: Review

“…Drawing parallels with human learning, where skills transfer across contexts, pre-trained neural networks such as VGG, ResNet, Inception, and MobileNet are widely employed as starting points. These models, accessible via platforms like Ten-sorFlow Model Garden and PyTorch Hub, facilitate efficient model adaptation [42][43][44][45][46] Transfer learning in computer vision makes use of pre-trained models and datasets to effectively address new tasks. By utilizing a pre-trained model as a foundational framework, known as a backbone model, practitioners minimize the necessity for extensive new data and annotations, thereby enhancing performance on the target task.…”

“…Drawing parallels with human learning, where skills transfer across contexts, pre-trained neural networks such as VGG, ResNet, Inception, and MobileNet are widely employed as starting points. These models, accessible via platforms like Tensor-Flow Model Garden and PyTorch Hub, facilitate efficient model adaptation [42][43][44][45][46]. Both local and cloud-based training strategies offer benefits, with local training granting control over configurations and cloud-based training providing scalability and potentially expedited processing times.…”