Downscaled training gradients are close to native only inside specific noise windows and on mild routes; the mismatch splits into a ratio-governed part and an absolute-size floor that persists at every noise level.
5): predicted safe boundaries𝑡 ∗ per route as the tolerance𝛿sweeps its range.𝛿 reenc is the measured re-encode noise floor, a zero-free-parameter anchor fixed by our own pipeline
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When does training on downscaled images yield the same gradients?
Downscaled training gradients are close to native only inside specific noise windows and on mild routes; the mismatch splits into a ratio-governed part and an absolute-size floor that persists at every noise level.