A new end-to-end training scheme for visual attribution maps that optimizes deletion and insertion metrics directly via differentiable ranking relaxation instead of surrogate objectives.
In: ICML (2017)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learn to Rank: Visual Attribution by Learning Importance Ranking
A new end-to-end training scheme for visual attribution maps that optimizes deletion and insertion metrics directly via differentiable ranking relaxation instead of surrogate objectives.