Lune

CVPR Findings2026

Catalyst: Out-of-Distribution Detection via Elastic Scaling

Abid Hassan, Tuan Ngo, Saad Shafiq, Nenad Medvidovic

Abstract

Out-of-distribution (OOD) detection is critical for the safe deployment of deep neural networks. State-of-the-art post-hoc methods typically derive OOD scores from the output logits or penultimate feature vector obtained via global average pooling (GAP). We contend that this exclusive reliance on the logit or feature vector discards a rich, complementary signal: the raw channel-wise statistics of the pre-pooling feature map lost in GAP. In this paper, we introduce Catalyst, a post-hoc framework that exploits these under-explored signals. Catalyst computes an input-dependent scaling factor (ω) on-the-fly from these raw statistics (e.g., mean, standard deviation, and maximum activation). This ω is then fused with the existing baseline score, multiplicatively modulating it -an "elastic scaling" -to push the ID and OOD distributions further apart. We demonstrate Catalyst is a generalizable framework: it seamlessly integrates with logit-based methods (e.g., Energy, ReAct, SCALE) and also provides a significant boost to distance-based detectors like KNN. As a result, Catalyst achieves substantial and consistent performance gains, reducing the average False Positive Rate by 32.87% on CIFAR-10 (ResNet-18), 27.94% on CIFAR-100 (ResNet-18), and 22.25% on ImageNet (ResNet-50). Our results highlight the untapped potential of pre-pooling statistics and demonstrate that Catalyst is complementary to existing OOD detection approaches. Our code is available here: https://github.com/bingabid/Catalyst

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • A ConvNet for the 2020s cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • ReAct: Out-of-distribution Detection With Rectified Activations cites Energy-based Out-of-distribution Detection
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites Energy-based Out-of-distribution Detection
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites ReAct: Out-of-distribution Detection With Rectified Activations
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on34

  1. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  2. A ConvNet for the 2020sZhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer et al.CVPR 2022 · 6,782 citations
  3. Energy-based Out-of-distribution DetectionWeitang Liu, Xiaoyun Wang, John D. Owens, Yixuan LiNeurIPS 2020 · 2,213 citations
  4. Out-of-Distribution Detection with Deep Nearest NeighborsYiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan LiICML 2022 · 789 citations
  5. ReAct: Out-of-distribution Detection With Rectified ActivationsYiyou Sun, Chuan Guo, Yixuan LiNeurIPS 2021 · 733 citations

Related papers

  1. Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementKai Xu, Rongyu Chen, Gianni Franchi, Angela YaoICLR 2024 · 81 citations
  2. Revisiting Logit Distributions for Reliable Out-of-Distribution DetectionJiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang et al.NeurIPS 2025 · 9 citations
  3. Hybrid Energy Based Model in the Feature Space for Out-of-Distribution DetectionMarc Lafon, Elias Ramzi, Clément Rambour, Nicolas ThomeICML 2023 · 14 citations
  4. GEN: Pushing the Limits of Softmax-Based Out-of-Distribution DetectionXixi Liu, Yaroslava Lochman, Christopher ZachCVPR 2023
  5. AdaSCALE: Adaptive Scaling for OOD DetectionSudarshan RegmiICML 2026 · 9 citations
Dusk over the sea between two cliffs drawn in fine vertical lines