Learning Distilled Collaboration Graph for Multi-Agent Perception

11/01/2021
by   Yiming Li, et al.
13

To promote better performance-bandwidth trade-off for multi-agent perception, we propose a novel distilled collaboration graph (DiscoGraph) to model trainable, pose-aware, and adaptive collaboration among agents. Our key novelties lie in two aspects. First, we propose a teacher-student framework to train DiscoGraph via knowledge distillation. The teacher model employs an early collaboration with holistic-view inputs; the student model is based on intermediate collaboration with single-view inputs. Our framework trains DiscoGraph by constraining post-collaboration feature maps in the student model to match the correspondences in the teacher model. Second, we propose a matrix-valued edge weight in DiscoGraph. In such a matrix, each element reflects the inter-agent attention at a specific spatial region, allowing an agent to adaptively highlight the informative regions. During inference, we only need to use the student model named as the distilled collaboration network (DiscoNet). Attributed to the teacher-student framework, multiple agents with the shared DiscoNet could collaboratively approach the performance of a hypothetical teacher model with a holistic view. Our approach is validated on V2X-Sim 1.0, a large-scale multi-agent perception dataset that we synthesized using CARLA and SUMO co-simulation. Our quantitative and qualitative experiments in multi-agent 3D object detection show that DiscoNet could not only achieve a better performance-bandwidth trade-off than the state-of-the-art collaborative perception methods, but also bring more straightforward design rationale. Our code is available on https://github.com/ai4ce/DiscoNet.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

page 9

page 10

page 16

04/11/2020

Inter-Region Affinity Distillation for Road Marking Segmentation

We study the problem of distilling knowledge from a large deep teacher n...
11/29/2021

Improved Knowledge Distillation via Adversarial Collaboration

Knowledge distillation has become an important approach to obtain a comp...
05/23/2019

Zero-shot Knowledge Transfer via Adversarial Belief Matching

Performing knowledge transfer from a large teacher network to a smaller ...
08/05/2021

MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets

Annotating multiple organs in 3D medical images is time-consuming and co...
12/17/2020

Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation

We propose a novel method based on teacher-student learning framework fo...
04/11/2019

Two Body Problem: Collaborative Visual Task Completion

Collaboration is a necessary skill to perform tasks that are beyond one ...
04/20/2021

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

We present Self-Ensembling Single-Stage object Detector (SE-SSD) for acc...

Code Repositories

DiscoNet

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.