19 papers
Same Loss, Different Gradients
Ningkang Peng, Xiaoqian Peng, Yifan He +4
Differentiable learning typically assumes that the scalar objective evaluated in the forward pass and the gradient supplied to the optimizer in the backward pass describe the same…
How Accurate Is Accurate Enough?
Ningkang Peng, Qianfeng Yu, Jingyang Mao +2
How accurate must a numerical approximation be within a learning system? Primitive error alone cannot answer this question: errors of the same magnitude can have very different con…
Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?
Ningkang Peng, Qianfeng Yu, Jingyang Mao +4
In probabilistic contrastive learning, a shared temperature is commonly interpreted as a shared similarity scale, but this interpretation does not hold for high-dimensional distrib…
Early High-Frequency Injection for Geometry-Sensitive OOD Detection
Chuanjie Cheng, Ningkang Peng, Chenxi Liu +3
Post-hoc OOD detectors score logits or features after training, so their success depends on the geometry already encoded in the representation. We revisit this assumption through a…
GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
Ningkang Peng, Jingyang Mao, Xiaoqian Peng +4
Deep neural networks (DNNs) experience significant performance degradation when processing noisy labels, primarily due to overfitting on mislabeled data. Current mainstream approac…
Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
Jingyang Mao, Ningkang Peng, Yanhui Gu
Learning with noisy labels in multimedia classification often combines external annotations and model predictions into a single reliability weight, even though the two sources can…
Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
Ningkang Peng, Xuanming Chen, Yanhui Gu
Long-tailed out-of-distribution (LT-OOD) detection is often addressed with specialized training, including auxiliary out-of-distribution (OOD) data, abstention heads, contrastive o…
When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
Ningkang Peng, Jingyang Mao, Runhan Zhou +2
Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject out-of-distribution (OOD) input…
Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
Ningkang Peng, Jingyang Mao, Xiaoqian Peng +2
Noisy-label methods often estimate sample reliability from forward-space signals such as loss, confidence, or entropy. These signals indicate whether a sample is difficult to predi…
HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
Ningkang Peng, Jingyang Mao, Qianfeng Yu +3
In large-scale visual recognition and data mining tasks, the presence of noisy labels severely undermines the generalization capability of deep neural networks (DNNs). Prevalent sa…
How to Achieve Prototypical Birth and Death for OOD Detection?
Ningkang Peng, Qianfeng Yu, Xiaoqian Peng +7
Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the mainstream strategies for ac…
PIS: A Physics-Informed System for Accurate State Partitioning of Protein Trajectories
Qianfeng Yu, Ningkang Peng, Yanhui Gu
Understanding the conformational evolution of -amyloid (), particularly the isoform, is fundamental to elucidating the pathogenic mechanisms underlying Alzheimer's…
Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion
Ningkang Peng, Kun Shao, Jingyang Mao +4
Deploying trustworthy AI in open-world environments faces a dual challenge: the necessity for robust Out-of-Distribution (OOD) detection to ensure system safety, and the demand for…
Halt the Hallucination: Decoupling Signal and Semantic OOD Detection Based on Cascaded Early Rejection
Ningkang Peng, Chuanjie Cheng, Jingyang Mao +7
Efficient and robust Out-of-Distribution (OOD) detection is paramount for safety-critical applications.However, existing methods still execute full-scale inference on low-level sta…
VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
Ningkang Peng, Qianfeng Yu, Yuhao Zhang +6
Out-of-Distribution (OOD) detection under long-tailed distributions is a highly challenging task because the scarcity of samples in tail classes leads to blurred decision boundarie…
Breaking Semantic Hegemony: Decoupling Principal and Residual Subspaces for Generalized OOD Detection
Ningkang Peng, Xiaoqian Peng, Yuhao Zhang +7
While feature-based post-hoc methods have made significant strides in Out-of-Distribution (OOD) detection, we uncover a counter-intuitive Simplicity Paradox in existing state-of-th…
Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection
Ningkang Peng, JiuTao Zhou, Yuhao Zhang +6
Out-of-distribution (OOD) detection is a critical task for the safe deployment of machine learning models in the real world. Existing prototype-based representation learning method…
Affordance-First Decomposition for Continual Learning in Video-Language Understanding
Mengzhu Xu, Hanzhi Liu, Ningkang Peng +2
Continual learning for video--language understanding is increasingly important as models face non-stationary data, domains, and query styles, yet prevailing solutions blur what sho…
A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection
Ningkang Peng, Yuzhe Mao, Yuhao Zhang +5
Out-of-Distribution (OOD) detection is a cornerstone for the safe deployment of AI systems in the open world. However, existing methods treat OOD detection as a binary classificati…