Search Results for author: Zsolt Kira

Found 42 papers, 28 papers with code

Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking

no code implementations1 Jul 2021 Nathaniel Glaser, Yen-Cheng Liu, Junjiao Tian, Zsolt Kira

In this paper, we address bandwidth-limited and obstruction-prone collaborative perception, specifically in the context of multi-agent semantic segmentation.

Semantic Segmentation

Enhancing Multi-Robot Perception via Learned Data Association

no code implementations1 Jul 2021 Nathaniel Glaser, Yen-Cheng Liu, Junjiao Tian, Zsolt Kira

In this paper, we address the multi-robot collaborative perception problem, specifically in the context of multi-view infilling for distributed semantic segmentation.

Semantic Segmentation

Striking the Right Balance: Recall Loss for Semantic Segmentation

1 code implementation28 Jun 2021 Junjiao Tian, Niluthpol Mithun, Zach Seymour, Han-Pang Chiu, Zsolt Kira

There are two major drawbacks to these methods: 1) constantly up-weighting minority classes can introduce excessive false positives in semantic segmentation; 2) a minority class is not necessarily a hard class.

Semantic Segmentation

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

1 code implementation17 Jun 2021 James Smith, Yen-Chang Hsu, Jonathan Balloch, Yilin Shen, Hongxia Jin, Zsolt Kira

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time.

class-incremental learning Incremental Learning

LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation

1 code implementation16 Mar 2021 Jingdao Chen, Zsolt Kira, Yong K. Cho

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks.

Instance Segmentation Point Cloud Segmentation +1

Unbiased Teacher for Semi-Supervised Object Detection

1 code implementation ICLR 2021 Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda

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.

Image Classification Object Detection +1

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer

1 code implementation23 Jan 2021 James Smith, Jonathan Balloch, Yen-Chang Hsu, Zsolt Kira

Our work investigates whether we can significantly reduce this memory budget by leveraging unlabeled data from an agent's environment in a realistic and challenging continual learning paradigm.

Continual Learning Knowledge Distillation

Recall Loss for Imbalanced Image Classification and Semantic Segmentation

1 code implementation1 Jan 2021 Junjiao Tian, Niluthpol Chowdhury Mithun, Zachary Seymour, Han-Pang Chiu, Zsolt Kira

Many works have proposed to weigh the standard cross entropy loss function with pre-computed weights based on class statistics such as the number of samples and class margins.

Classification General Classification +3

Posterior Re-calibration for Imbalanced Datasets

no code implementations NeurIPS 2020 Junjiao Tian, Yen-Cheng Liu, Nathan Glaser, Yen-Chang Hsu, Zsolt Kira

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.

Long-tail Learning Semantic Segmentation

3D for Free: Crossmodal Transfer Learning using HD Maps

no code implementations24 Aug 2020 Benjamin Wilson, Zsolt Kira, James Hays

In this work, we address the long-tail problem by leveraging both the large class-taxonomies of modern 2D datasets and the robustness of state-of-the-art 2D detection methods.

3D Object Detection Autonomous Driving +3

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

2 code implementations ECCV 2020 Chia-Wen Kuo, Chih-Yao Ma, Jia-Bin Huang, Zsolt Kira

Recent state-of-the-art semi-supervised learning (SSL) methods use a combination of image-based transformations and consistency regularization as core components.

Data Augmentation Semi-Supervised Image Classification

Frustratingly Simple Domain Generalization via Image Stylization

2 code implementations19 Jun 2020 Nathan Somavarapu, Chih-Yao Ma, Zsolt Kira

Convolutional Neural Networks (CNNs) show impressive performance in the standard classification setting where training and testing data are drawn i. i. d.

Domain Generalization Image Stylization

When2com: Multi-Agent Perception via Communication Graph Grouping

1 code implementation CVPR 2020 Yen-Cheng Liu, Junjiao Tian, Nathaniel Glaser, Zsolt Kira

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.

Who2com: Collaborative Perception via Learnable Handshake Communication

no code implementations21 Mar 2020 Yen-Cheng Liu, Junjiao Tian, Chih-Yao Ma, Nathan Glaser, Chia-Wen Kuo, Zsolt Kira

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.

Multi-agent Reinforcement Learning Scene Understanding +1

Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data

2 code implementations CVPR 2020 Yen-Chang Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise.

Out-of-Distribution Detection

UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation

no code implementations6 Nov 2019 Junjiao Tian, Wesley Cheung, Nathan Glaser, Yen-Cheng Liu, Zsolt Kira

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.

Semantic Segmentation

Temporal Attentive Alignment for Large-Scale Video Domain Adaptation

5 code implementations ICCV 2019 Min-Hung Chen, Zsolt Kira, Ghassan AlRegib, Jaekwon Yoo, Ruxin Chen, Jian Zheng

Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e. g. 7. 9% accuracy gain over "Source only" from 73. 9% to 81. 8% on "HMDB --> UCF", and 10. 3% gain on "Kinetics --> Gameplay").

Domain Adaptation

Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification

no code implementations12 Jun 2019 Chia-Wen Kuo, Chih-Yao Ma, Jia-Bin Huang, Zsolt Kira

We then show that when combined with these regularizers, the proposed method facilitates the propagation of information from generated prototypes to image data to further improve results.

Classification General Classification +1

Learning to Generate Grounded Visual Captions without Localization Supervision

2 code implementations1 Jun 2019 Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib, Peter Vajda, Marcus Rohrbach, Zsolt Kira

When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the model is hallucinating based on priors in the dataset and/or the language model.

Image Captioning Language Modelling +1

Leveraging Semantics for Incremental Learning in Multi-Relational Embeddings

no code implementations29 May 2019 Angel Daruna, Weiyu Liu, Zsolt Kira, Sonia Chernova

Service robots benefit from encoding information in semantically meaningful ways to enable more robust task execution.

Incremental Learning Knowledge Graphs

Temporal Attentive Alignment for Video Domain Adaptation

5 code implementations26 May 2019 Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets.

Domain Adaptation

Path Ranking with Attention to Type Hierarchies

1 code implementation26 May 2019 Weiyu Liu, Angel Daruna, Zsolt Kira, Sonia Chernova

The objective of the knowledge base completion problem is to infer missing information from existing facts in a knowledge base.

Knowledge Base Completion Knowledge Graphs

The Regretful Navigation Agent for Vision-and-Language Navigation

1 code implementation CVPR 2019 (Oral) 2019 Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira

As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making.

Decision Making Vision and Language Navigation +2

Multi-view Incremental Segmentation of 3D Point Clouds for Mobile Robots

1 code implementation18 Feb 2019 Jingdao Chen, Yong K. Cho, Zsolt Kira

Mobile robots need to create high-definition 3D maps of the environment for applications such as remote surveillance and infrastructure mapping.


Multi-class Classification without Multi-class Labels

1 code implementation ICLR 2019 Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira

This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation.

Classification General Classification +1

Data-Efficient Graph Embedding Learning for PCB Component Detection

no code implementations16 Nov 2018 Chia-Wen Kuo, Jacob Ashmore, David Huggins, Zsolt Kira

This paper presents a challenging computer vision task, namely the detection of generic components on a PCB, and a novel set of deep-learning methods that are able to jointly leverage the appearance of individual components and the propagation of information across the structure of the board to accurately detect and identify various types of components on a PCB.

Graph Embedding Object Detection +1

A probabilistic constrained clustering for transfer learning and image category discovery

no code implementations28 Jun 2018 Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira

The proposed objective directly minimizes the negative log-likelihood of cluster assignment with respect to the pairwise constraints, has no hyper-parameters, and demonstrates improved scalability and performance on both supervised learning and unsupervised transfer learning.

Deep Clustering Ecg Risk Stratification +1

Learning to Cluster for Proposal-Free Instance Segmentation

1 code implementation17 Mar 2018 Yen-Chang Hsu, Zheng Xu, Zsolt Kira, Jiawei Huang

We utilize the most fundamental property of instance labeling -- the pairwise relationship between pixels -- as the supervision to formulate the learning objective, then apply it to train a fully convolutional network (FCN) for learning to perform pixel-wise clustering.

Autonomous Driving Instance Segmentation +3

Learning to cluster in order to transfer across domains and tasks

1 code implementation ICLR 2018 Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira

The key insight is that, in addition to features, we can transfer similarity information and this is sufficient to learn a similarity function and clustering network to perform both domain adaptation and cross-task transfer learning.

Transfer Learning Unsupervised Domain Adaptation

Grounded Objects and Interactions for Video Captioning

no code implementations16 Nov 2017 Chih-Yao Ma, Asim Kadav, Iain Melvin, Zsolt Kira, Ghassan AlRegib, Hans Peter Graf

We address the problem of video captioning by grounding language generation on object interactions in the video.

Scene Understanding Text Generation +2

On Convergence and Stability of GANs

8 code implementations ICLR 2018 Naveen Kodali, Jacob Abernethy, James Hays, Zsolt Kira

We propose studying GAN training dynamics as regret minimization, which is in contrast to the popular view that there is consistent minimization of a divergence between real and generated distributions.

TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition

4 code implementations30 Mar 2017 Chih-Yao Ma, Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.

Action Classification Action Recognition +1

Deep Image Category Discovery using a Transferred Similarity Function

no code implementations5 Dec 2016 Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira

We propose that this network can be learned with contrastive loss which is only based on weak binary pair-wise constraints.

Transfer Learning

A Continuous Optimization Approach for Efficient and Accurate Scene Flow

no code implementations27 Jul 2016 Zhaoyang Lv, Chris Beall, Pablo F. Alcantarilla, Fuxin Li, Zsolt Kira, Frank Dellaert

We propose a continuous optimization method for solving dense 3D scene flow problems from stereo imagery.

Neural network-based clustering using pairwise constraints

2 code implementations19 Nov 2015 Yen-Chang Hsu, Zsolt Kira

Robustness analysis also shows that the method is largely insensitive to the number of clusters.

Cannot find the paper you are looking for? You can Submit a new open access paper.