Related papers: SpawnNet: Learning Generalizable Visuomotor Skills…

Value iteration networks (VINs) have been demonstrated to have a good generalization ability for reinforcement learning tasks across similar domains. However, based on our experiments, a policy learned by VINs still fail to generalize well…

The utilization of broad datasets has proven to be crucial for generalization for a wide range of fields. However, how to effectively make use of diverse multi-task data for novel downstream tasks still remains a grand challenge in…

In this paper, we build upon two major recent developments in the field, Diffusion Policies for visuomotor manipulation and large pre-trained multimodal foundational models to obtain a robotic skill learning system. The system can obtain…

In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a trained generative…

Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms. Perhaps due to this diversity, previous work has typically relied on…

Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs. Unfortunately, their applicability is hampered by the computational complexity associated with performing message passing on…

Generative Flow Networks for continuous scenarios (CFlowNets) have shown promise in solving sequential decision-making tasks by learning stochastic policies using a flow and a retrieval network. Despite their demonstrated efficiency…

Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness for industrial visual inspection remains unclear. Industrial data differ substantially…

Robot learning methods have the potential for widespread generalization across tasks, environments, and objects. However, these methods require large diverse datasets that are expensive to collect in real-world robotics settings. For robot…

It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit that pretraining on…

We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a…

A robot working in a physical environment (like home or factory) needs to learn to use various available tools for accomplishing different tasks, for instance, a mop for cleaning and a tray for carrying objects. The number of possible tools…

We present semi-supervised deep learning approaches for traversability estimation from fisheye images. Our method, GONet, and the proposed extensions leverage Generative Adversarial Networks (GANs) to effectively predict whether the area…

Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph's nodes and edges are…

Deep reinforcement learning policies, despite their outstanding efficiency in simulated visual control tasks, have shown disappointing ability to generalize across disturbances in the input training images. Changes in image statistics or…

Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…

Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively…

Generative Flow Networks (GFlowNets) have emerged as a powerful paradigm for generating composite structures, demonstrating considerable promise across diverse applications. While substantial progress has been made in exploring their…

Transfer learning from supervised ImageNet models has been frequently used in medical image analysis. Yet, no large-scale evaluation has been conducted to benchmark the efficacy of newly-developed pre-training techniques for medical image…

In this paper, we propose SwarmNet -- a neural network architecture that can learn to predict and imitate the behavior of an observed swarm of agents in a centralized manner. Tested on artificially generated swarm motion data, the network…