Computer Vision Explainable AI Visual correspondence-based explanations improve AI robustness and human-AI team accuracy July 26, 2022
Computer Vision Explainable AI DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover’s Distance Improves Out-Of-Distribution Face Identification December 13, 2022
Computer Vision Explainable AI Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers November 8, 2024
Explainable AI NLP Double Trouble: How to not explain a text classifier’s decisions using counterfactuals synthesized by masked language models October 22, 2022
![At an optimal confidence threshold, CYWS [25] (top row) sometimes still produces false positives—□ in (a) & (c)—and fails to detect changes (a). Dashed - - - boxes show groundtruth changes. First, we encourage detectors to be more aware of changes via a novel contrastive loss. Second, our Hungarian-based post-processing reduces false positives (a), improves change-detection accuracy (b), and estimates correspondences (c–d), i.e., paired changes such as (□, □) and (□, □). Our work (bottom row) is the first to estimate change correspondences compared to prior works [25, 26, 40] (top row).](https://anhnguyen.me/wp-content/uploads/2025/05/change-detection-teaser.jpg)
