mlsanityData to 14 Oct 2026

Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Segmentation

arXiv 2605.29773 ↗First posted 28 May 2026cs.CV cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Reliable semantic segmentation for mobile robots requires both accurate dense prediction and robust uncertainty estimation under distribution shift. Strong uncertainty baselines such as Monte Carlo Dropout often require repeated stochastic forward passes and are difficult to deploy on edge platforms. We propose Energy-Aware NECO, a single-pass pixel-wise out-of-distribution (OOD) detector for semantic segmentation. The method combines a centered NECO-style geometric ratio computed from decoder features with a logit-based Energy score. Both components are standardized using statistics fitted on a pure in-distribution validation split and fused through a convex combination. We evaluate the method on the miniMUAD subset using true pixel-level OOD labels. The proposed hybrid score achieves an AUROC of 0.8539, outperforming NECO-only (0.8280), Energy-only (0.8171), and an ensemble predictive-entropy baseline (0.8124). Additional qualitative and operating-point analyses show that the hybrid detector improves overall ranking performance while preserving the efficiency advantages of a single-pass design. Code is available at https://github.com/boyuan-zhangx/Energy-Aware_NECO

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 25 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

24 of 25 references.

References · 24

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,299
12 more
  1. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  2. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  3. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  4. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  5. 2020Local Temperature Scaling for Probability Calibrationcited by 95
  6. 2023Unmasking Anomalies in Road-Scene Segmentationcited by 45
  7. 2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
  8. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  9. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  10. 2022Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detectioncited by 15
  11. 2024AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Drivingcited by 14
  12. 2023Hybrid Open-set Segmentation with Synthetic Negative Datacited by 8

Built on by

Not cited yet.