Towards In-distribution Compatibility in Out-of-distribution Detection
Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. To address this defect, state-of-the-art solutions choose to train deep networks on an auxiliary dataset of outliers. Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions. However, we find that these intuitively designed outlier training criteria can hurt in-distribution learning and eventually lead to inferior performance. To this end, we identify three causes of the in-distribution incompatibility: contradictory gradient, false likelihood, and distribution shift. Based on our new understandings, we propose a new out-of-distribution detection method by adapting both the top-design of deep models and the loss function. Our method achieves in-distribution compatibility by pursuing less interference with the probabilistic characteristic of in-distribution features. On several benchmarks, our method not only achieves the state-of-the-art out-of-distribution detection performance but also improves the in-distribution accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Out-of-Distribution DetectionSimilar Papers 제목 키워드 기반
Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning
To facilitate reliable deployments of autonomous robots in the real world, Out-of-Distribution (OOD) detection capabilities are often required. A powerful approach for OOD detection is based on density estimation with No…
2D Object DetectionDensity Estimationobject-detectionObject Detection+2Self-Compatibility: Evaluating Causal Discovery without Ground Truth
As causal ground truth is incredibly rare, causal discovery algorithms are commonly only evaluated on simulated data. This is concerning, given that simulations reflect preconceptions about generating processes regarding…
Causal DiscoveryModel SelectionThe Inflation Technique Completely Solves the Causal Compatibility Problem
The causal compatibility question asks whether a given causal structure graph -- possibly involving latent variables -- constitutes a genuinely plausible causal explanation for a given probability distribution over the g…
Causal InferenceOn the Generative Utility of Cyclic Conditionals
We study whether and how can we model a joint distribution $p(x,z)$ using two conditional models $p(x|z)$ and $q(z|x)$ that form a cycle. This is motivated by the observation that deep generative models, in addition to a…
A Metacognitive Approach to Out-of-Distribution Detection for Segmentation
Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world. To improve out-of-distribution (OOD)…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionScene SegmentationSegmentation+1