Pith. sign in

REVIEW 1 cited by

AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.06462 v4 pith:TBHDG655 submitted 2024-01-12 cs.CV cs.HC

classification cs.CVcs.HC
keywords modeldataattributionscannerfindingmodelsslicesystemanalytics
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance, often characterized by distinct feature sets or descriptive metadata. However, in the context of validating vision models involving unstructured image data, this approach faces significant challenges, including the laborious and costly requirement for additional metadata and the complex task of interpreting the root causes of underperformance. To address these challenges, we introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for metadata-free data slice finding. Our system identifies interpretable data slices that involve common model behaviors and visualizes these patterns through an Attribution Mosaic design. Our interactive interface provides straightforward guidance for users to detect, interpret, and annotate predominant model issues, such as spurious correlations (model biases) and mislabeled data, with minimal effort. Additionally, it employs a cutting-edge model regularization technique to mitigate the detected issues and enhance the model's performance. The efficacy of AttributionScanner is demonstrated through use cases involving two benchmark datasets, with qualitative and quantitative evaluations showcasing its substantial effectiveness in vision model validation, ultimately leading to more reliable and accurate models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. VISTA: A Visual Analytics Framework to Enhance Foundation Model-Generated Data Labels

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A human-in-the-loop visual analytics system that detects, summarizes, and corrects label and alignment errors in foundation-model-generated image segmentation data, improving downstream open-vocabulary segmentation pe...

Pith tools