paper-with-me

홈 › Papers

Towards In-distribution Compatibility in Out-of-distribution Detection

2022-08-29 · Boxi Wu, Jie Jiang, Haidong Ren, Zifan Du, Wenxiao Wang, Zhifeng Li, Deng Cai, Xiaofei He, Binbin Lin, Wei Liu

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.

📄 PDF Abstract BibTeX arXiv:2208.13433

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning

2023-11-11 · Jianxiang Feng, JongSeok Lee, Simon Geisler, Stephan Gunnemann 외

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+2

Self-Compatibility: Evaluating Causal Discovery without Ground Truth

2023-07-18 · Philipp M. Faller, Leena Chennuru Vankadara, Atalanti A. Mastakouri, Francesco Locatello 외

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 Selection

The Inflation Technique Completely Solves the Causal Compatibility Problem

2017-07-20 · Miguel Navascues, Elie Wolfe

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 Inference

On the Generative Utility of Cyclic Conditionals

2021-06-30 · NeurIPS 2021 12 · Chang Liu, Haoyue Tang, Tao Qin, Jintao Wang 외

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

2023-10-04 · Meghna Gummadi, Cassandra Kent, Karl Schmeckpeper, Eric Eaton

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