← Back to all news
arXiv Machine Learning By Rahim Hossain, Md Tawheedul Islam Bhuian, Md Farhan Shadiq, Kyoung-Don Kang

MM++: Post-Hoc Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion

Read the original on arXiv Machine Learning →

MM++ (Multilayer Mahalanobis++) is a post‑hoc, scale‑invariant framework for out‑of‑distribution detection that builds a joint feature space by selecting discriminative intermediate layers based on entropy density drops and fusing them with the final representation. It uses a Ledoit‑Wolf regularized tied covariance matrix to stabilize the space, allowing reliable distance estimation without requiring auxiliary OOD data, classifier fine‑tuning, or architectural changes. The method achieves robust performance across different architectures for both near‑ and far‑OOD scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jun 24

From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection

arXiv:2606. 23825v1 Announce Type: cross Abstract: Efficient small object detection is bottlenecked by the inherent feature scarcity of tiny targets, which is further aggravated by operations of spatial-domain detectors that indiscriminately discard critical high-frequency details.

By Yuhan Rui, Shihan Qiao, Yibin Lou, Mingxi Yu, Yutong Wan, Yanqiao Chen, Dongsheng Hou, Zhen Cao, Athena Zhuoming Zhong, Qi Hao
llmscomputer-visionbenchmarks
More like this →
arXiv Computer Vision
Aug 27

Context-Guided Semantic Alignment for Feature Fusion Networks

The paper introduces Feature Interaction Network (FINE), a lightweight semantic alignment module for feature fusion networks in object detectors. FINE refines low‑level features using high‑level contextual guidance through cross‑level attention, and employs Alignment‑Aware Token Sampling to reduce attention complexity. The resulting spatial‑channel modulation map selectively enhances semantically relevant pixels while preserving sub‑pixel localization, leading to improved detection accuracy with minimal computational overhead.

By Hyungseop Lee, Jiho Lee, Woochul Kang
safety
More like this →