REVIEW 7 cited by
Energy-based Out-of-distribution Detection
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density of the inputs and are less susceptible to the overconfidence issue. Within this framework, energy can be flexibly used as a scoring function for any pre-trained neural classifier as well as a trainable cost function to shape the energy surface explicitly for OOD detection. On a CIFAR-10 pre-trained WideResNet, using the energy score reduces the average FPR (at TPR 95%) by 18.03% compared to the softmax confidence score. With energy-based training, our method outperforms the state-of-the-art on common benchmarks.
Forward citations
Cited by 7 Pith papers
-
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
OS-level defenses against self-hosted AI agents that corrupt their own memory/config files can close most attack cells but cannot detect small in-distribution memory edits, leaving a residual surface.
-
Representation Trajectories Matters: Complementary Evidence for OOD Detection and Image Classification
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.
-
Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA
Replacing fixed top-k routing in MoE-LoRA with router-confidence-based nucleus admission plus an expert-disagreement extension improves accuracy and OOD detection at matched average compute.
-
Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition
NOODLE corrects noisy labels with a transition matrix and cleans features via low-rank sparse decomposition, improving OOD detection under label noise.
-
A Variational Information Theoretic Approach to Out-of-Distribution Detection
A variational loss combining KL divergence and the Information Bottleneck predicts a piecewise-linear shaping function for OOD detection that beats existing element-wise shaping methods on ImageNet and CIFAR benchmarks.
-
Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
An energy-based scoring head trained on dense embeddings improves abstention decisions for medical RAG systems on semantically hard out-of-distribution queries compared to softmax and kNN baselines.
-
Topological Uncertainty for Anomaly Detection in the Neural-network EoS Inference with Neutron Star Data
Applying Topological Uncertainty to hidden-layer activations of a trained FNN detects failed neutron-star EoS inferences with over 90% success in the best-tested configuration.
Discussion (0). Sign in to comment.