paper-with-me

홈 › Papers

Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units

2019-07-05 · Lakmal Meegahapola, Vengateswaran Subramaniam, Lance Kaplan, Archan Misra

In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We show that the combined neural activations of such a hidden layer have class-specific distributional properties, and then define multiple statistical measures to compute how far a test sample's activations deviate from such distributions. Using a variety of benchmark datasets (including MNIST, CIFAR10, Fashion-MNIST & notMNIST), we show how such PAD-based measures can be used, independent of any training technique, to (a) derive fine-grained uncertainty estimates for inferences; (b) provide inferencing accuracy competitive with alternatives that require execution of the full pipeline, and (c) reliably isolate out-of-distribution test samples.

📄 PDF Abstract BibTeX arXiv:1907.02711

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Versatile Physics-based Character Control with Hybrid Latent Representation

2025-03-17 · Jinseok Bae, Jungdam Won, Donggeun Lim, Inwoo Hwang 외

We present a versatile latent representation that enables physically simulated character to efficiently utilize motion priors. To build a powerful motion embedding that is shared across multiple tasks, the physics contro…

Motion Generationmotion in-betweeningQuantization

Self-Distribution Binary Neural Networks

2021-03-03 · Ping Xue, Yang Lu, Jingfei Chang, Xing Wei 외

In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i.e., 1-bit representation). Feature representation is critical for deep neural networks, while in BNNs, the …

Quantization

The Spotlight Resonance Method: Resolving the Alignment of Embedded Activations

2025-05-09 · George Bird

Understanding how deep learning models represent data is currently difficult due to the limited number of methodologies available. This paper demonstrates a versatile and novel visualisation tool for determining the axis…

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

2026-05-28 · Yingdong Shi, Ruiming Zhang, Changming Li, Zhiyu Yang 외 arxiv

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style…

Instruction Following

Exploring Versatile Prior for Human Motion via Motion Frequency Guidance

2021-11-25 · Jiachen Xu, Min Wang, Jingyu Gong, Wentao Liu 외

Prior plays an important role in providing the plausible constraint on human motion. Previous works design motion priors following a variety of paradigms under different circumstances, leading to the lack of versatility.…

DenoisingRepresentation Learning