Three Steps to Multimodal Trajectory Prediction: Modality Clustering,
Classification and Synthesis
- URL: http://arxiv.org/abs/2103.07854v1
- Date: Sun, 14 Mar 2021 06:21:03 GMT
- Title: Three Steps to Multimodal Trajectory Prediction: Modality Clustering,
Classification and Synthesis
- Authors: Jianhua Sun, Yuxuan Li, Hao-Shu Fang, Cewu Lu
- Abstract summary: We present a novel insight along with a brand-new prediction framework.
Our proposed method surpasses state-of-the-art works even without introducing social and map information.
- Score: 54.249502356251085
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multimodal prediction results are essential for trajectory forecasting task
as there is no single correct answer for the future. Previous frameworks can be
divided into three categories: regression, generation and classification
frameworks. However, these frameworks have weaknesses in different aspects so
that they cannot model the multimodal prediction task comprehensively. In this
paper, we present a novel insight along with a brand-new prediction framework
by formulating multimodal prediction into three steps: modality clustering,
classification and synthesis, and address the shortcomings of earlier
frameworks. Exhaustive experiments on popular benchmarks have demonstrated that
our proposed method surpasses state-of-the-art works even without introducing
social and map information. Specifically, we achieve 19.2% and 20.8%
improvement on ADE and FDE respectively on ETH/UCY dataset. Our code will be
made publicly available.
Related papers
- On the Evaluation Consistency of Attribution-based Explanations [42.1421504321572]
We introduce Meta-Rank, an open platform for benchmarking attribution methods in the image domain.
Our benchmark reveals three insights in attribution evaluation endeavors: 1) evaluating attribution methods under disparate settings can yield divergent performance rankings; 2) although inconsistent across numerous cases, the performance rankings exhibit remarkable consistency across distinct checkpoints along the same training trajectory; and 3) prior attempts at consistent evaluation fare no better than baselines when extended to more heterogeneous models and datasets.
arXiv Detail & Related papers (2024-07-28T11:49:06Z) - Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification [120.37051160567277]
This paper proposes a novel measure named Top-K Pairwise Ranking (TKPR)
A series of analyses show that TKPR is compatible with existing ranking-based measures.
On the other hand, we establish a sharp generalization bound for the proposed framework based on a novel technique named data-dependent contraction.
arXiv Detail & Related papers (2024-07-09T09:36:37Z) - Deep Neural Network Benchmarks for Selective Classification [27.098996474946446]
Multiple selective classification frameworks exist, most of which rely on deep neural network architectures.
We evaluate these approaches using several criteria, including selective error rate, empirical coverage, distribution of rejected instance's classes, and performance on out-of-distribution instances.
arXiv Detail & Related papers (2024-01-23T12:15:47Z) - Performance Comparison of Session-based Recommendation Algorithms based on GNNs [6.617487928813376]
In session-based recommendation settings, a recommender system has no access to long-term user profiles.
We present the results of an evaluation of eight recent GNN-based approaches that were published in high-quality outlets.
arXiv Detail & Related papers (2023-12-27T19:24:26Z) - Hierarchical Audio-Visual Information Fusion with Multi-label Joint
Decoding for MER 2023 [51.95161901441527]
In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions.
Deep features extracted from foundation models are used as robust acoustic and visual representations of raw video.
Our final system achieves state-of-the-art performance and ranks third on the leaderboard on MER-MULTI sub-challenge.
arXiv Detail & Related papers (2023-09-11T03:19:10Z) - Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory
Forecasting [39.73793468422024]
This work first proposes a novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from interaction modules.
We build a general CU-aware regression framework with an original permutation-equivariant uncertainty estimator to do both tasks of regression and uncertainty estimation.
We apply the proposed framework to current SOTA multi-agent trajectory forecasting systems as a plugin module.
arXiv Detail & Related papers (2022-07-11T21:17:41Z) - Set-valued classification -- overview via a unified framework [15.109906768606644]
Multi-class datasets can be extremely ambiguous and single-output predictions fail to deliver satisfactory performance.
By allowing predictors to predict a set of label candidates, set-valued classification offers a natural way to deal with this ambiguity.
We provide infinite sample optimal set-valued classification strategies and review a general plug-in principle to construct data-driven algorithms.
arXiv Detail & Related papers (2021-02-24T14:54:07Z) - Margin-Based Transfer Bounds for Meta Learning with Deep Feature
Embedding [67.09827634481712]
We leverage margin theory and statistical learning theory to establish three margin-based transfer bounds for meta-learning based multiclass classification (MLMC)
These bounds reveal that the expected error of a given classification algorithm for a future task can be estimated with the average empirical error on a finite number of previous tasks.
Experiments on three benchmarks show that these margin-based models still achieve competitive performance.
arXiv Detail & Related papers (2020-12-02T23:50:51Z) - SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction [72.37440317774556]
We propose advances that address two key challenges in future trajectory prediction.
multimodality in both training data and predictions and constant time inference regardless of number of agents.
arXiv Detail & Related papers (2020-07-26T08:17:10Z) - Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples.
We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries.
We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
arXiv Detail & Related papers (2020-02-27T10:22:17Z)
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.