Database Paper Browser

Back to papers

Demonstration of VCR: A Tabular Data Slicing Approach to Understanding Object Detection Model Performance

Summary: VCR converts segment-level concepts from vision foundation models into tabular, interpretable features combined with image metadata to enable slice discovery for object detection. It uses scalable frequent-itemset mining to find systematic failure slices and supports iterative refinement. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13681
Venue
VLDB
Year
2024
Pagerank
4.1945683e-05
Overall Rank
11,121 | 22.64%
DOI
10.14778/3685800.3685898

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 3 of 3 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
36 Fast Algorithms for Mining Association Rules 1994 VLDB 0.00076161096
3,162 Looking for Trouble: Analyzing Classifier Behavior via Pattern Divergence 2021 SIGMOD 7.4589576e-05
6,903 POEM: Pattern-Oriented Explanations of Convolutional Neural Networks 2023 VLDB 4.8925595e-05
Previous Page 1 / 1 Next

Semantically Similar Papers