Improving Online Performance Prediction for Semantic Segmentation

• URL: http://arxiv.org/abs/2104.05255v1
• Date: Mon, 12 Apr 2021 07:44:40 GMT
• Title: Improving Online Performance Prediction for Semantic Segmentation
• Authors: Marvin Klingner, Andreas B\"ar, Marcel Mross, Tim Fingscheidt
• Abstract summary: We address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation. Many high-level decisions rely on such DNNs, which are usually evaluated offline, while their performance in online operation remains unknown. We propose an improved online performance prediction scheme, building on a recently proposed concept of predicting the primary semantic segmentation task's performance.
• Score: 29.726236358091295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i.e., during inference, which is of high importance in safety-critical applications such as autonomous driving. Here, many high-level decisions rely on such DNNs, which are usually evaluated offline, while their performance in online operation remains unknown. To solve this problem, we propose an improved online performance prediction scheme, building on a recently proposed concept of predicting the primary semantic segmentation task's performance. This can be achieved by evaluating the auxiliary task of monocular depth estimation with a measurement supplied by a LiDAR sensor and a subsequent regression to the semantic segmentation performance. In particular, we propose (i) sequential training methods for both tasks in a multi-task training setup, (ii) to share the encoder as well as parts of the decoder between both task's networks for improved efficiency, and (iii) a temporal statistics aggregation method, which significantly reduces the performance prediction error at the cost of a small algorithmic latency. Evaluation on the KITTI dataset shows that all three aspects improve the performance prediction compared to previous approaches.

Related papers

• Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation [69.60321475454843]
  We propose DPCPL, the first pre-training and prompt-tuning paradigm tailored for Multi-Behavior Sequential Recommendation. In the pre-training stage, we propose a novel Efficient Behavior Miner (EBM) to filter out the noise at multiple time scales. Subsequently, we propose to tune the pre-trained model in a highly efficient manner with the proposed Customized Prompt Learning (CPL) module.
  arXiv  Detail & Related papers  (2024-08-21T06:48:38Z)
• An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing [8.892147201091726]
  We propose an end-to-end reinforcement learning based order-dispatching approach in Didi. We employ a two-layer Decision Process framework to model this problem, and present underlineDeep underlineDouble underlineScalable underlineNetwork (DSN2), an encoder-decoder structure network to generate order assignments. By leveraging contextual dynamics, our approach can adapt to the behavioral patterns for better performance.
  arXiv  Detail & Related papers  (2024-08-20T01:30:53Z)
• A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction [6.137256382926171]
  This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet) The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets.
  arXiv  Detail & Related papers  (2024-06-26T03:59:21Z)
• AIO-P: Expanding Neural Performance Predictors Beyond Image Classification [22.743278613519152]
  We propose a novel All-in-One Predictor (AIO-P) to pretrain neural predictors on architecture examples. AIO-P can achieve Mean Absolute Error (MAE) and Spearman's Rank Correlation (SRCC) below 1% and above 0.5, respectively.
  arXiv  Detail & Related papers  (2022-11-30T18:30:41Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation [87.54604263202941]
  We propose a tiny deep neural network of which partial layers are iteratively exploited for refining its previous estimations. We employ learned gating criteria to decide whether to exit from the weight-sharing loop, allowing per-sample adaptation in our model. Our method consistently outperforms state-of-the-art 2D/3D hand pose estimation approaches in terms of both accuracy and efficiency for widely used benchmarks.
  arXiv  Detail & Related papers  (2021-11-11T23:31:34Z)
• Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions [80.78077900288868]
  We decompose the design methodology of early-exit networks to its key components and survey the recent advances in each one of them. We position early-exiting against other efficient inference solutions and provide our insights on the current challenges and most promising future directions for research in the field.
  arXiv  Detail & Related papers  (2021-06-09T12:33:02Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [87.1188556802942]
  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. We propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.
  arXiv  Detail & Related papers  (2021-05-17T13:42:09Z)

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.