activity
20172022
most citedSelf-Monitoring Navigation Agent via Auxiliary Progress Estimation

134 citations · 398 across the 27 of their papers we have counts for

collaborators

43 papers

cs.LG2023

ConstraintMatch for Semi-constrained Clustering

Jann Goschenhofer, Bernd Bischl, Zsolt Kira

Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine, while still yielding full-supervisi…

cs.LG20222 cited

System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games

Indranil Sur, Zachary Daniels, Abrar Rahman +16

As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adap…

cs.CV2022

Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation

Chia-Wen Kuo, Chih-Yao Ma, Judy Hoffman +1

In Vision-and-Language Navigation (VLN), researchers typically take an image encoder pre-trained on ImageNet without fine-tuning on the environments that the agent will be trained…

cs.CV20221 cited

On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition

Farrukh Rahman, Ömer Mubarek, Zsolt Kira

Recently vision transformers have been shown to be competitive with convolution-based methods (CNNs) broadly across multiple vision tasks. The less restrictive inductive bias of tr…

cs.CV202215 cited

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian +2

Adapting large-scale pretrained models to various downstream tasks via fine-tuning is a standard method in machine learning. Recently, parameter-efficient fine-tuning methods show…

cs.LG20222 cited

FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization

Junjiao Tian, James Seale Smith, Zsolt Kira

Federated Learning (FL) seeks to distribute model training across local clients without collecting data in a centralized data-center, hence removing data-privacy concerns. A major…