In this paper, we address the multi-robot collaborative perception problem, specifically in the context of multi-view infilling for distributed semantic segmentation.
In this paper, we address bandwidth-limited and obstruction-prone collaborative perception, specifically in the context of multi-agent semantic segmentation.
To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
Neural Networks can perform poorly when the training label distribution is heavily imbalanced, as well as when the testing data differs from the training distribution.
Ranked #10 on Long-tail Learning on CIFAR-100-LT (ρ=100)
While significant advances have been made for single-agent perception, many applications require multiple sensing agents and cross-agent communication due to benefits such as coverage and robustness.
In this paper, we propose the problem of collaborative perception, where robots can combine their local observations with those of neighboring agents in a learnable way to improve accuracy on a perception task.
Specifically, we analyze a number of uncertainty measures, each of which captures a different aspect of uncertainty, and we propose a novel way to fuse degraded inputs by scaling modality-specific output softmax probabilities.
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.
Continual learning has received a great deal of attention recently with several approaches being proposed.
We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains.
Person re-identification (Re-ID) aims at recognizing the same person from images taken across different cameras.
Ranked #16 on Unsupervised Domain Adaptation on Duke to Market
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated.