OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples

Chen, Changjian; Yuan, Jun; Lu, Yafeng; Liu, Yang; Su, Hang; Yuan, Songtao; Liu, Shixia

doi:10.1109/tvcg.2020.2973258

Cited by 61 publications

(50 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To support the exploration of images and their detected objects, a matrix and a grid layout are used, which have shown their advantage to support content-level analysis [49]. The highest level in the image hierarchy is displayed as a matrix (Fig.…”

Section: Visualization Of Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Towards Better Caption Supervision for Object Detection

Chen¹,

Wu²,

Wang³

et al. 2022

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Visualization Of Imagesmentioning

confidence: 99%

“…Each cell in the grid layout represents an image. The locations of the cells are determined by the kNN-based grid layout algorithm proposed in [49], which first projects images on a 2D plane as scattered points using t-SNE and then assigns these points to grid cells by solving a linear assignment problem. This layout algorithm places similar images together.…”

mentioning

confidence: 99%

Towards Better Caption Supervision for Object Detection

Chen¹,

Wu²,

Wang³

et al. 2022

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

“…OoD samples are test samples that are not well covered by training data, which is a major source of model performance degradation. To tackle this issue, Chen et al [21] proposed OoDAnalyzer to detect and analyze OoD samples. An ensemble OoD detection method, combining both high-and low-level features, was proposed to improve detection accuracy.…”

Section: Instance-level Improvementmentioning

confidence: 99%

“…OoDAnalyzer, an interactive method to detect out-of-distribution samples and explain them in context. Reproduced with permission from Ref [21],. c IEEE 2020.…”

mentioning

confidence: 99%

A survey of visual analytics techniques for machine learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

Visual analytics for machine learning has recently evolved as one of the most exciting areas in the field of visualization. To better identify which research topics are promising and to learn how to apply relevant techniques in visual analytics, we systematically review 259 papers published in the last ten years together with representative works before 2010. We build a taxonomy, which includes three first-level categories: techniques before model building, techniques during modeling building, and techniques after model building. Each category is further characterized by representative analysis tasks, and each task is exemplified by a set of recent influential works. We also discuss and highlight research challenges and promising potential future research opportunities useful for visual analytics researchers.

show abstract

“…Based on the analysis focus, these works can roughly be categorized into three groups. The first group concentrates on the input data of ML models to better understand the data distribution [8,63] or to better select the high-dimensional data features [25,39]. The second group focuses on the intermediate data representations from ML models to interpret how the data has been transformed internally.…”

Section: Related Workmentioning

confidence: 99%

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

Rathore¹,

Dev²,

Phillips³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1. With VERB, users can explore the high-dimensional word representations interactively before, during, and after applying bias mitigation techniques. (A) Embedding View highlights a subset of word embeddings using dimensionality reduction and visualizes the step-by-step transformations of their embeddings across various debiasing techniques. (B) Control Panel enables users to configure each debiasing technique and provides controls to iterate through each step of the transformation. (C) Explanation Panel gives a step-by-step description of the transformation. In this example, in the Embedding View, word representations are reoriented with the concept direction (Gender) along the x-axis. They are then transformed by a debiasing technique called the Linear Projection that removes this concept. These transformed representations are visualized again in (D) after a new dimensionality reduction, where there is no longer a well-defined gender concept, and hence the stereotypical associations are mitigated.

show abstract

OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples

Cited by 61 publications

References 43 publications

Towards Better Caption Supervision for Object Detection

Towards Better Caption Supervision for Object Detection

A survey of visual analytics techniques for machine learning

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

Contact Info

Product

Resources

About