Songcan Chen

Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning

2019 · arXiv (Cornell University)

In the process of exploring the world, the curiosity constantly drives humans to cognize new things. Supposing you are a zoologist, for a presented animal image, you can recognize it immediately if you know its …

Semi-Supervised Multimodal Relevance Vector Regression Improves Cognitive Performance Estimation from Imaging and Biological Biomarkers

2020 · UNC Libraries

Accurate estimation of cognitive scores for patients can help track the progress of neurological diseases. In this paper, we present a novel semi-supervised multimodal relevance vector regression (SM-RVR) method for predicting clinical scores of neurological …

Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learning

2023 · arXiv (Cornell University)

Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise. However, a more common scenario in the real world is the presence of both open-set and closed-set noise. Existing …

All-around Neural Collapse for Imbalanced Classification

2024 · arXiv (Cornell University)

Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach \textit{optimal} inter-class separability during the terminal phase of training on a \textit{balanced} dataset. Once …

HGLTR: Hierarchical Knowledge Injection for Calibrating Pre-trained Models in Long-Tail Recognition

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Long-tail recognition remains challenging for pre-trained foundation models like CLIP, which often suffer from performance degradation under imbalanced data. This stems not only from the overfitting/underfitting issues during fine-tuning but, more fundamentally, from the inherent …