NECO: NEural Collapse Based Out-of-distribution detection
Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that `neural collapse'', a phenomenon affecting in-distribution data for models trained beyond loss convergence, also influences OOD data. To benefit from this interplay, we introduce NECO, a novel post-hoc method for OOD detection, which leverages the geometric properties of `neural collapse'' and of principal component spaces to identify OOD data. Our extensive experiments demonstrate that NECO achieves state-of-the-art results on both small and large-scale OOD detection tasks while exhibiting strong generalization capabilities across different network architectures. Furthermore, we provide a theoretical explanation for the effectiveness of our method in OOD detection. Code is available at https://gitlab.com/drti/neco
Code (1)
Tasks
Out-of-Distribution DetectionSimilar Papers 제목 키워드 기반
Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
Reliable semantic segmentation for mobile robots requires both accurate dense prediction and robust uncertainty estimation under distribution shift. Strong uncertainty baselines such as Monte Carlo Dropout often require …
Out-of-Distribution DetectionSemantic SegmentationFineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection
Recently introduced ControlNet has the ability to steer the text-driven image generation process with geometric input such as human 2D pose, or edge features. While ControlNet provides control over the geometric form of …
Image GenerationLineCounter: Learning Handwritten Text Line Segmentation by Counting
Handwritten Text Line Segmentation (HTLS) is a low-level but important task for many higher-level document processing tasks like handwritten text recognition. It is often formulated in terms of semantic segmentation or o…
Handwritten Text Recognitionobject-detectionObject DetectionSegmentation+1LineConGraphs: Line Conversation Graphs for Effective Emotion Recognition using Graph Neural Networks
Emotion Recognition in Conversations (ERC) is a critical aspect of affective computing, and it has many practical applications in healthcare, education, chatbots, and social media platforms. Earlier approaches for ERC an…
Emotion RecognitionGraph Attentiongraph constructionGraph Neural NetworkLaneCorrect: Self-supervised Lane Detection
Lane detection has evolved highly functional autonomous driving system to understand driving scenes even under complex environments. In this paper, we work towards developing a generalized computer vision system able to …
Autonomous DrivingLane Detection