SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks

• URL: http://arxiv.org/abs/2206.08427v1
• Date: Thu, 16 Jun 2022 20:03:31 GMT
• Title: SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks
• Authors: Ajay Subramanian, Sara Price, Omkar Kumbhar, Elena Sizikova, Najib J. Majaj, Denis G. Pelli
• Abstract summary: People show a flexible tradeoff between speed and accuracy. We present the first large-scale dataset of the speed-accuracy tradeoff (SAT) in recognizing ImageNet images. We compare networks with humans on curve-fit error, category-wise correlation, and curve steepness.
• Score: 0.45438205344305216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The core of everyday tasks like reading and driving is active object recognition. Attempts to model such tasks are currently stymied by the inability to incorporate time. People show a flexible tradeoff between speed and accuracy and this tradeoff is a crucial human skill. Deep neural networks have emerged as promising candidates for predicting peak human object recognition performance and neural activity. However, modeling the temporal dimension i.e., the speed-accuracy tradeoff (SAT), is essential for them to serve as useful computational models for how humans recognize objects. To this end, we here present the first large-scale (148 observers, 4 neural networks, 8 tasks) dataset of the speed-accuracy tradeoff (SAT) in recognizing ImageNet images. In each human trial, a beep, indicating the desired reaction time, sounds at a fixed delay after the image is presented, and observer's response counts only if it occurs near the time of the beep. In a series of blocks, we test many beep latencies, i.e., reaction times. We observe that human accuracy increases with reaction time and proceed to compare its characteristics with the behavior of several dynamic neural networks that are capable of inference-time adaptive computation. Using FLOPs as an analog for reaction time, we compare networks with humans on curve-fit error, category-wise correlation, and curve steepness, and conclude that cascaded dynamic neural networks are a promising model of human reaction time in object recognition tasks.

Related papers

• RTify: Aligning Deep Neural Networks with Human Behavioral Decisions [10.510746720313303]
  Current neural network models of primate vision focus on replicating overall levels of behavioral accuracy. We introduce a novel computational framework to model the dynamics of human behavioral choices by learning to align the temporal dynamics of a recurrent neural network to human reaction times (RTs) We show that the approximation can be used to optimize an "ideal-observer" RNN model to achieve an optimal tradeoff between speed and accuracy without human data.
  arXiv  Detail & Related papers  (2024-11-06T03:04:05Z)
• Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning [91.29876772547348]
  Spiking neural networks (SNNs) are investigated as biologically inspired models of neural computation. This paper reveals that SNNs, when amalgamated with synaptic delay and temporal coding, are proficient in executing (knowledge) graph reasoning.
  arXiv  Detail & Related papers  (2024-05-27T05:53:30Z)
• A Dynamical Model of Neural Scaling Laws [79.59705237659547]
  We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
  arXiv  Detail & Related papers  (2024-02-02T01:41:38Z)
• Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes [29.592870472342337]
  This work presents the temporal conditioning spiking latent variable models (TeCoS-LVM) to simulate the neural response to natural visual stimuli. We use spiking neurons to produce spike outputs that directly match the recorded trains. We show that TeCoS-LVM models can produce more realistic spike activities and accurately fit spike statistics than powerful alternatives.
  arXiv  Detail & Related papers  (2023-06-21T06:30:18Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
  Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
  arXiv  Detail & Related papers  (2023-04-14T09:39:06Z)
• SpikiLi: A Spiking Simulation of LiDAR based Real-time Object Detection for Autonomous Driving [0.0]
  Spiking Neural Networks are a new neural network design approach that promises tremendous improvements in power efficiency, computation efficiency, and processing latency. We first illustrate the applicability of spiking neural networks to a complex deep learning task namely Lidar based 3D object detection for automated driving.
  arXiv  Detail & Related papers  (2022-06-06T20:05:17Z)
• Ensemble perspective for understanding temporal credit assignment [1.9843222704723809]
  We show that each individual connection in recurrent neural networks is modeled by a spike and slab distribution, rather than a precise weight value. Our model reveals important connections that determine the overall performance of the network. It is thus promising to study the temporal credit assignment in recurrent neural networks from the ensemble perspective.
  arXiv  Detail & Related papers  (2021-02-07T08:14:05Z)
• Anytime Prediction as a Model of Human Reaction Time [0.0]
  We study the effect of difficulty on human reaction time in a classification network. 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. We conclude that Anytime classification is a promising model for human reaction time in recognition tasks.
  arXiv  Detail & Related papers  (2020-11-25T16:30:52Z)
• Fast Motion Understanding with Spatiotemporal Neural Networks and Dynamic Vision Sensors [99.94079901071163]
  This paper presents a Dynamic Vision Sensor (DVS) based system for reasoning about high speed motion. We consider the case of a robot at rest reacting to a small, fast approaching object at speeds higher than 15m/s. We highlight the results of our system to a toy dart moving at 23.4m/s with a 24.73deg error in $theta$, 18.4mm average discretized radius prediction error, and 25.03% median time to collision prediction error.
  arXiv  Detail & Related papers  (2020-11-18T17:55:07Z)
• Event-based Asynchronous Sparse Convolutional Networks [54.094244806123235]
  Event cameras are bio-inspired sensors that respond to per-pixel brightness changes in the form of asynchronous and sparse "events" We present a general framework for converting models trained on synchronous image-like event representations into asynchronous models with identical output. We show both theoretically and experimentally that this drastically reduces the computational complexity and latency of high-capacity, synchronous neural networks.
  arXiv  Detail & Related papers  (2020-03-20T08:39:49Z)

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.