# Stream-based Active Learning by Exploiting Temporal Properties in Perception with Temporal Predicted Loss

arXiv: https://arxiv.org/abs/2309.05517 · HTML: https://mlsanity.com/paper/2309.05517/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 11 Sep 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [Efficient Uncertainty Estimation for Semantic Segmentation in Videos](https://mlsanity.com/paper/1807.11037/) (2018)
- [Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector](https://mlsanity.com/paper/1901.10609/) (2019)
- [Temporal Coherence for Active Learning in Videos](https://mlsanity.com/paper/1908.11757/) (2019)
- [Submodular Streaming in All its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity](https://mlsanity.com/paper/1905.00948/) (2019)
- [Stream-based active learning with linear models](https://mlsanity.com/paper/2207.09874/) (2022)
- [Bayesian Active Learning for Sim-to-Real Robotic Perception](https://mlsanity.com/paper/2109.11547/) (2021)
- [Active Learning for Deep Neural Networks on Edge Devices](https://mlsanity.com/paper/2106.10836/) (2021)
- [Episode-Based Active Learning with Bayesian Neural Networks](https://mlsanity.com/paper/1703.07473/) (2017)

## Built on by (most cited first, 6 of 6)

- [Uncertainty for Active Learning on Graphs](https://mlsanity.com/paper/2405.01462/) (2024)
- [A Unified Approach Towards Active Learning and Out-of-Distribution Detection](https://mlsanity.com/paper/2405.11337/) (2024)
- [Joint Out-of-Distribution Filtering and Data Discovery Active Learning](https://mlsanity.com/paper/2503.02491/) (2025)
- [Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation](https://mlsanity.com/paper/2504.04841/) (2025)
- [Stream-Based Active Learning for Process Monitoring](https://mlsanity.com/paper/2411.12563/) (2024)
- [A Machine Learning Perspective on Automated Driving Corner Cases](https://mlsanity.com/paper/2510.10653/) (2025)

## Abstract (arXiv)

Active learning (AL) reduces the amount of labeled data needed to train a machine learning model by intelligently choosing which instances to label. Classic pool-based AL requires all data to be present in a datacenter, which can be challenging with the increasing amounts of data needed in deep learning. However, AL on mobile devices and robots, like autonomous cars, can filter the data from perception sensor streams before reaching the datacenter. We exploited the temporal properties for such image streams in our work and proposed the novel temporal predicted loss (TPL) method. To evaluate the stream-based setting properly, we introduced the GTA V streets and the A2D2 streets dataset and made both publicly available. Our experiments showed that our approach significantly improves the diversity of the selection while being an uncertainty-based method. As pool-based approaches are more common in perception applications, we derived a concept for comparing pool-based and stream-based AL, where TPL out-performed state-of-the-art pool- or stream-based approaches for different models. TPL demonstrated a gain of 2.5 precept points (pp) less required data while being significantly faster than pool-based methods.