Small or off-center objects make ImageNet-trained models depend more on background cues, and current debiasing methods do not fix this.
17 Published in Transactions on Machine Learning Research (08/2025) 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 mIOU 0 50 100 150 200Frequency A vg
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models
Small or off-center objects make ImageNet-trained models depend more on background cues, and current debiasing methods do not fix this.