← Search

Pei Peng

2 accepted papers

2025

Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition

NeurIPS 2025poster

Object–context shortcuts remain a persistent challenge in vision‑language models, undermining zero‑shot reliability when test-time scenes diverge from familiar training co-occurrences. We recast this issue as a causal inference problem and ask: Would the prediction remain if the object appeared in a…

Cited by 0SourceScholar
2024

Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training

ICML 2024poster

The key to multi-label image classification (MLC) is to improve model performance by leveraging label correlations. Unfortunately, it has been shown that overemphasizing co-occurrence relationships can cause the overfitting issue of the model, ultimately leading to performance degradation. In this p…