Jihua Huang

Jihua Huang, Yi Yao, Ajay Divakaran

We introduce a novel framework for temporal causal discovery and inference that addresses two key challenges: complex nonlinear dependencies and spurious correlations. Our approach employs a multi-layer Transformer-based time-series forecaster to capture long-range, nonlinear temporal relationships among variables. After training, we extract the underlying causal structure and associated time lags from the forecaster using gradient-based analysis, enabling the construction of a causal graph. To mitigate the impact of spurious causal relationships, we introduce a prior knowledge integration mechanism based on attention masking, which consistently enforces user-excluded causal links across multiple Transformer layers. Extensive experiments show that our method significantly outperforms other state-of-the-art approaches, achieving a 12.8% improvement in F1-score for causal discovery and 98.9% accuracy in estimating causal lags.

Jihua Huang, Amir Tamrakar

We propose a novel facial Anchors and Contours Estimation framework, ACE-Net, for fine-level face alignment tasks. ACE-Net predicts facial anchors and contours that are richer than traditional facial landmarks while overcoming ambiguities and inconsistencies in their definitions. We introduce a weakly supervised loss enabling ACE-Net to learn from existing facial landmarks datasets without the need for reannotation. Instead, synthetic data, from which GT contours can be easily obtained, is used during training to bridge the density gap between landmarks and true facial contours. We evaluate the face alignment accuracy of ACE-Net with respect to the HELEN dataset which has 194 annotated facial landmarks, while it is trained with only 68 or 36 landmarks from the 300-W dataset. We show that ACE-Net generated contours are better than contours interpolated straight from the 68 GT landmarks and ACE-Net also outperforms models trained only with full supervision from GT landmarks-based contours.

Karan Sikka, Jihua Huang, Andrew Silberfarb et al.

We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as novel neuro-symbolic loss functions that regularize visual-semantic embedding. CSNL forces visual features in the VSE to obey common-sense rules relating to hypernyms and attributes. We introduce two key novelties for improved learning: (1) enforcement of rules for a group instead of a single concept to take into account class-wise relationships, and (2) confidence margins inside logical operators that enable implicit curriculum learning and prevent premature overfitting. We evaluate the advantages of incorporating each knowledge source and show consistent gains over prior state-of-art methods in both conventional and generalized ZSL e.g. 11.5%, 5.5%, and 11.6% improvements on AWA2, CUB, and Kinetics respectively.