Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machine learning models in real-world applications. Previous paradigms either explore better scoring functions or utilize the knowledge of outliers to equip the models with the ability of OOD detection. However, few of them pay attention to the intrinsic OOD detection capability of the given model. In this work, we generally discover the existence of an intermediate stage of a model trained on in-distribution (ID) data having higher OOD detection performance than that of its final stage across different settings, and further identify one critical data-level attribution to be learning with the atypical samples. Based on such insights, we propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data. Our method utilizes a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them. Extensive experiments and analysis demonstrate the effectiveness of our method. The code is available at: https://github.com/tmlr-group/Unleashing-Mask.
Code (1)
Tasks
Out-of-Distribution DetectionSimilar Papers 제목 키워드 기반
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need
The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, wh…
AllOut-of-Distribution Detection3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis
Face presentation attacks have become a major threat to face recognition systems and many countermeasures have been proposed in the past decade. However, most of them are devoted to 2D face presentation attacks, rather t…
Face RecognitionIntrinsic Image DecompositionLogits-Based Finetuning
The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, wh…
Out of Distribution (OOD) DetectionMIMEx: Intrinsic Rewards from Masked Input Modeling
Exploring in environments with high-dimensional observations is hard. One promising approach for exploration is to use intrinsic rewards, which often boils down to estimating "novelty" of states, transitions, or trajecto…
PredictionYou Can Mask More For Extremely Low-Bitrate Image Compression
Learned image compression (LIC) methods have experienced significant progress during recent years. However, these methods are primarily dedicated to optimizing the rate-distortion (R-D) performance at medium and high bit…
Image Compression