Hierarchical Visual Feature Fusion for Robust Out‐of‐Distribution Detection under Semantic and Image‐Level Covariate Shifts

Abstract Deep neural networks (DNNs) have become a fundamental component of modern visual computing systems, yet their reliability often degrades on out‐of‐distribution (OOD) inputs, i.e., test images that deviate from the training distribution. Such deviations may arise from high‐level semantic shifts, where images belong to unseen categories, or from image‐level covariate shifts, such as noise, blur, illumination changes, and compression artifacts. Although covariate shifts often preserve the original class identity, they can substantially distort low‐level visual statistics and alter model responses, making them difficult to detect with methods designed primarily for semantic novelty. This challenge becomes more severe when semantic and covariate shifts coexist, as they jointly affect different levels of visual abstraction. To address this issue, we propose AFDisc, a unified OOD detection framework that exploits the hierarchical representations of DNNs. AFDisc is motivated by the observation that shallow features are more sensitive to appearance variations, while deep features encode richer semantic information. Based on this complementarity, we introduce an attentive fusion module that adaptively integrates appearance‐sensitive cues from shallow layers and semantic cues from deep layers into a unified representation for detecting diverse distribution shifts. We further construct auxiliary supervision signals through controlled appearance perturbations, enabling the model to better capture the spectrum of real‐world visual degradations. Extensive experiments under semantic and covariate shift settings demonstrate AFDisc's effectiveness and its superior performance over prior state‐of‐the‐art methods.

Authors

Institutions

Publication Details

Journal
Computer Graphics Forum
Published
2026-11-13
DOI
https://doi.org/10.1111/cgf.70619
Primary Topic
Adversarial Robustness in Machine Learning
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Hierarchical Visual Feature Fusion for Robust Out‐of‐Distribution Detection under Semantic and Image‐Level Covariate Shifts

Keke Tang, Tao Xiang, Chuan Ma, Ziyong Du et al.
2 links
Computer Graphics Forum
Adversarial Robustness in Machine Learning
article

Hierarchical Visual Feature Fusion for Robust Out‐of‐Distribution Detection under Semantic and Image‐Level Covariate Shifts

Keke Tang, Tao Xiang, Chuan Ma, Ziyong Du, Xiao Lv, Shengfeng He, Chao Hou, Bin Zhu
article en

Abstract

Abstract Deep neural networks (DNNs) have become a fundamental component of modern visual computing systems, yet their reliability often degrades on out‐of‐distribution (OOD) inputs, i.e., test images that deviate from the training distribution. Such deviations may arise from high‐level semantic shifts, where images belong to unseen categories, or from image‐level covariate shifts, such as noise, blur, illumination changes, and compression artifacts. Although covariate shifts often preserve the original class identity, they can substantially distort low‐level visual statistics and alter model responses, making them difficult to detect with methods designed primarily for semantic novelty. This challenge becomes more severe when semantic and covariate shifts coexist, as they jointly affect different levels of visual abstraction. To address this issue, we propose AFDisc, a unified OOD detection framework that exploits the hierarchical representations of DNNs. AFDisc is motivated by the observation that shallow features are more sensitive to appearance variations, while deep features encode richer semantic information. Based on this complementarity, we introduce an attentive fusion module that adaptively integrates appearance‐sensitive cues from shallow layers and semantic cues from deep layers into a unified representation for detecting diverse distribution shifts. We further construct auxiliary supervision signals through controlled appearance perturbations, enabling the model to better capture the spectrum of real‐world visual degradations. Extensive experiments under semantic and covariate shift settings demonstrate AFDisc's effectiveness and its superior performance over prior state‐of‐the‐art methods.

Computer Graphics Forum
Chongqing University (CN), Guangzhou University (CN), Singapore Management University (SG)
National Natural Science Foundation of China, Graduate School, Chongqing University
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon