Anytime Prediction as a Model of Human Reaction Time
Neural networks today often recognize objects as well as people do, and thus might serve as models of the human recognition process. However, most such networks provide their answer after a fixed computational effort, whereas human reaction time varies, e.g. from 0.2 to 10 s, depending on the properties of stimulus and task. To model the effect of difficulty on human reaction time, we considered a classification network that uses early-exit classifiers to make anytime predictions. Comparing human and MSDNet accuracy in classifying CIFAR-10 images in added Gaussian noise, we find that the network equivalent input noise SD is 15 times higher than human, and that human efficiency is only 0.6\% that of the network. When appropriate amounts of noise are present to bring the two observers (human and network) into the same accuracy range, they show very similar dependence on duration or FLOPS, i.e. very similar speed-accuracy tradeoff. We conclude that Anytime classification (i.e. early exits) is a promising model for human reaction time in recognition tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionSimilar Papers 제목 키워드 기반
AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations
Anytime 3D human pose forecasting is crucial to synchronous real-world human-machine interaction, where the term ``anytime" corresponds to predicting human pose at any real-valued time step. However, to the best of our k…
Human Pose ForecastingAnytime Dense Prediction with Confidence Adaptivity
Anytime inference requires a model to make a progression of predictions which might be halted at any time. Prior research on anytime visual recognition has mostly focused on image classification. We propose the first uni…
image-classificationImage ClassificationPose EstimationPrediction+1You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection
We introduce AnytimeYOLO, a family of variants of the YOLO architecture that enables anytime object detection. Our AnytimeYOLO networks allow for interruptible inference, i.e., they provide a prediction at any point in t…
object-detectionObject DetectionAnytime Recognition of Objects and Scenes
Humans are capable of perceiving a scene at a glance, and obtain deeper understanding with additional time. Similarly, visual recognition deployments should be robust to varying computational budgets. Such situations req…
General ClassificationObject RecognitionSpeedMachines: Anytime Structured Prediction
Structured prediction plays a central role in machine learning applications from computational biology to computer vision. These models require significantly more computation than unstructured models, and, in many applic…
General ClassificationPredictionScene UnderstandingStructured Prediction