Pith. sign in

REVIEW 10 cited by

Extremely Simple Activation Shaping for Out-of-Distribution Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.09858 v2 pith:SODHEMVZ submitted 2022-09-20 cs.LG cs.CV

Andrija Djurisic , Nebojsa Bozanic , Arjun Ashok , Rosanne Liu This is my paper
classification cs.LGcs.CV
keywords trainingdetectionactivationout-of-distributionshapingsimpledatadeployment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The separation between training and deployment of machine learning models implies that not all scenarios encountered in deployment can be anticipated during training, and therefore relying solely on advancements in training has its limits. Out-of-distribution (OOD) detection is an important area that stress-tests a model's ability to handle unseen situations: Do models know when they don't know? Existing OOD detection methods either incur extra training steps, additional data or make nontrivial modifications to the trained network. In contrast, in this work, we propose an extremely simple, post-hoc, on-the-fly activation shaping method, ASH, where a large portion (e.g. 90%) of a sample's activation at a late layer is removed, and the rest (e.g. 10%) simplified or lightly adjusted. The shaping is applied at inference time, and does not require any statistics calculated from training data. Experiments show that such a simple treatment enhances in-distribution and out-of-distribution distinction so as to allow state-of-the-art OOD detection on ImageNet, and does not noticeably deteriorate the in-distribution accuracy. Video, animation and code can be found at: https://andrijazz.github.io/ash

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CURE-OOD: Benchmarking Out-of-Distribution Detection for Survival Prediction

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    CURE-OOD is the first benchmark for evaluating OOD detection in survival prediction under controlled CT acquisition shifts, showing that standard detectors often fail and providing a survival-aware baseline.

  2. Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories

    cs.LG 2025-10 unverdicted novelty 7.0 of 10

    DISC extracts multi-statistic trajectories from diffusion denoising to both detect and classify types of distributional shifts in OOD data.

  3. Representation Trajectories Matters: Complementary Evidence for OOD Detection and Image Classification

    cs.CV 2026-07 accept novelty 6.0 of 10

    Recording how an image's representation evolves block-by-block, relative to learned class routes, improves OOD detection in 131/152 comparisons and clean classification in 71/72 model–dataset cases.

  4. LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated Driving

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    LFA aggregates multi-layer backbone features via attention to improve run-time prediction of 2D object detector failures, outperforming single-layer baselines on KITTI and BDD100K.

  5. Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SynOOD generates synthetic near-boundary OOD images with MLLM-guided inpainting and energy-score gradients, then fine-tunes CLIP image and text features, reporting state-of-the-art OOD detection on ImageNet benchmarks.

  6. ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

    cs.LG 2024-02 unverdicted novelty 6.0 of 10

    ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and I...

  7. Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.

  8. Multi-Method Ensemble for Out-of-Distribution Detection

    cs.CV 2025-08 conditional novelty 5.0 of 10

    MME, a product of SCALE, VRA, fDBD, PCA, ViM, NME+ and CO+ scores, shows state-of-the-art OOD detection on common benchmarks, with a theoretical guarantee that is weaker than claimed.

  9. Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    KR-NFT tunes CLIP text features with image-conditioned scaling and shifting plus a knowledge regularization loss, improving OOD detection on base and unseen classes without forgetting pre-trained knowledge.

  10. Feature Bank Enhancement for Distance-based Out-of-Distribution Detection

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Clipping per-dimension outlier features in the training feature bank improves distance-based out-of-distribution detection on ImageNet-1k and CIFAR-10.

Pith tools