Localizing the foreground before classification and fusing its classifier output with the full-image prediction improves accuracy and robustness to background shifts in supervised and zero-shot VLM recognition.
Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bringing the Context Back into Object Recognition, Robustly
Localizing the foreground before classification and fusing its classifier output with the full-image prediction improves accuracy and robustness to background shifts in supervised and zero-shot VLM recognition.