VFDS: Variational Foresight Dynamic Selection in Bayesian Neural
Networks for Efficient Human Activity Recognition
- URL: http://arxiv.org/abs/2204.00130v1
- Date: Thu, 31 Mar 2022 22:52:43 GMT
- Title: VFDS: Variational Foresight Dynamic Selection in Bayesian Neural
Networks for Efficient Human Activity Recognition
- Authors: Randy Ardywibowo, Shahin Boluki, Zhangyang Wang, Bobak Mortazavi,
Shuai Huang, Xiaoning Qian
- Abstract summary: Variational Foresight Dynamic Selection (VFDS) learns a policy that selects the next feature subset to observe.
We apply VFDS on the Human Activity Recognition (HAR) task where the performance-cost trade-off is critical in its practice.
- Score: 81.29900407096977
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In many machine learning tasks, input features with varying degrees of
predictive capability are acquired at varying costs. In order to optimize the
performance-cost trade-off, one would select features to observe a priori.
However, given the changing context with previous observations, the subset of
predictive features to select may change dynamically. Therefore, we face the
challenging new problem of foresight dynamic selection (FDS): finding a dynamic
and light-weight policy to decide which features to observe next, before
actually observing them, for overall performance-cost trade-offs. To tackle
FDS, this paper proposes a Bayesian learning framework of Variational Foresight
Dynamic Selection (VFDS). VFDS learns a policy that selects the next feature
subset to observe, by optimizing a variational Bayesian objective that
characterizes the trade-off between model performance and feature cost. At its
core is an implicit variational distribution on binary gates that are dependent
on previous observations, which will select the next subset of features to
observe. We apply VFDS on the Human Activity Recognition (HAR) task where the
performance-cost trade-off is critical in its practice. Extensive results
demonstrate that VFDS selects different features under changing contexts,
notably saving sensory costs while maintaining or improving the HAR accuracy.
Moreover, the features that VFDS dynamically select are shown to be
interpretable and associated with the different activity types. We will release
the code.
Related papers
- AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable
Diffusion Model [69.12623428463573]
AlignDiff is a novel framework to quantify human preferences, covering abstractness, and guide diffusion planning.
It can accurately match user-customized behaviors and efficiently switch from one to another.
We demonstrate its superior performance on preference matching, switching, and covering compared to other baselines.
arXiv Detail & Related papers (2023-10-03T13:53:08Z) - Exploiting Modality-Specific Features For Multi-Modal Manipulation
Detection And Grounding [54.49214267905562]
We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks.
Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment.
We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
arXiv Detail & Related papers (2023-09-22T06:55:41Z) - Learning Diverse Features in Vision Transformers for Improved
Generalization [15.905065768434403]
We show that vision transformers (ViTs) tend to extract robust and spurious features with distinct attention heads.
As a result of this modularity, their performance under distribution shifts can be significantly improved at test time.
We propose a method to further enhance the diversity and complement of the learned features by encouragingarity of the attention heads' input gradients.
arXiv Detail & Related papers (2023-08-30T19:04:34Z) - Estimating Conditional Mutual Information for Dynamic Feature Selection [14.50261153230204]
Dynamic feature selection is a promising paradigm to reduce feature acquisition costs and provide transparency into the prediction process.
Here, we take an information-theoretic perspective and prioritize features based on their mutual information with the response variable.
We introduce several further improvements: allowing variable feature budgets across samples, enabling non-uniform costs between features, incorporating prior information, and exploring modern architectures to handle partial input information.
arXiv Detail & Related papers (2023-06-05T23:03:03Z) - MT-SLVR: Multi-Task Self-Supervised Learning for Transformation
In(Variant) Representations [2.94944680995069]
We propose a multi-task self-supervised framework (MT-SLVR) that learns both variant and invariant features in a parameter-efficient manner.
We evaluate our approach on few-shot classification tasks drawn from a variety of audio domains and demonstrate improved classification performance.
arXiv Detail & Related papers (2023-05-29T09:10:50Z) - Remembering What Is Important: A Factorised Multi-Head Retrieval and
Auxiliary Memory Stabilisation Scheme for Human Motion Prediction [41.34294145237618]
This paper presents an innovative auxiliary-memory-powered deep neural network framework for the improved modelling of historical knowledge.
We disentangle subject-specific, task-specific, and other auxiliary information from the observed pose sequences and utilise these factorised features to query the memory.
Two novel loss functions are introduced to encourage diversity within the auxiliary memory while ensuring the stability of the memory contents.
arXiv Detail & Related papers (2023-05-19T02:44:58Z) - ASPEST: Bridging the Gap Between Active Learning and Selective
Prediction [56.001808843574395]
Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain.
Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples.
In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
arXiv Detail & Related papers (2023-04-07T23:51:07Z) - Explaining Cross-Domain Recognition with Interpretable Deep Classifier [100.63114424262234]
Interpretable Deep (IDC) learns the nearest source samples of a target sample as evidence upon which the classifier makes the decision.
Our IDC leads to a more explainable model with almost no accuracy degradation and effectively calibrates classification for optimum reject options.
arXiv Detail & Related papers (2022-11-15T15:58:56Z) - Adaptive Discrete Communication Bottlenecks with Dynamic Vector
Quantization [76.68866368409216]
We propose learning to dynamically select discretization tightness conditioned on inputs.
We show that dynamically varying tightness in communication bottlenecks can improve model performance on visual reasoning and reinforcement learning tasks.
arXiv Detail & Related papers (2022-02-02T23:54:26Z) - Discriminative and Semantic Feature Selection for Place Recognition
towards Dynamic Environments [12.973423183330961]
We propose a discriminative and semantic feature selection network, dubbed as DSFeat.
Supervised by both semantic information and attention mechanism, we can estimate pixel-wise stability of features.
It should be noticed that our proposal can be readily pluggable into any feature-based SLAM system.
arXiv Detail & Related papers (2021-03-18T05:11:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.