Search Results for author: Tomas Pfister

Found 32 papers, 15 papers with code

Learning Fast Sample Re-weighting Without Reward Data

1 code implementation7 Sep 2021 Zizhao Zhang, Tomas Pfister

Training sample re-weighting is an effective approach for tackling data biases such as imbalanced and corrupted labels.

Meta-Learning

Controlling Neural Networks with Rule Representations

no code implementations14 Jun 2021 Sungyong Seo, Sercan O. Arik, Jinsung Yoon, Xiang Zhang, Kihyuk Sohn, Tomas Pfister

The key aspect of DeepCTRL is that it does not require retraining to adapt the rule strength -- at inference, the user can adjust it based on the desired operation point on accuracy vs. rule verification ratio.

Decision Making

Self-Trained One-class Classification for Unsupervised Anomaly Detection

no code implementations11 Jun 2021 Jinsung Yoon, Kihyuk Sohn, Chun-Liang Li, Sercan O. Arik, Chen-Yu Lee, Tomas Pfister

In experiments, we show the efficacy of our method for unsupervised anomaly detection on benchmarks from image and tabular data domains.

Classification Unsupervised Anomaly Detection

Aggregating Nested Transformers

3 code implementations26 May 2021 Zizhao Zhang, Han Zhang, Long Zhao, Ting Chen, Tomas Pfister

In this work, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical manner.

Image Classification Image Generation

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

1 code implementation CVPR 2021 Chun-Liang Li, Kihyuk Sohn, Jinsung Yoon, Tomas Pfister

We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data.

Ranked #5 on Anomaly Detection on MVTec AD (using extra training data)

Anomaly Detection Data Augmentation +4

Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts

no code implementations11 Jan 2021 Kunpeng Li, Zizhao Zhang, Guanhang Wu, Xuehan Xiong, Chen-Yu Lee, Zhichao Lu, Yun Fu, Tomas Pfister

To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.

Action Recognition

Exploring Sub-Pseudo Labels for Learning from Weakly-Labeled Web Videos

no code implementations1 Jan 2021 Kunpeng Li, Zizhao Zhang, Guanhang Wu, Xuehan Xiong, Chen-Yu Lee, Yun Fu, Tomas Pfister

To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.

Action Recognition

Differentiable Top-k with Optimal Transport

no code implementations NeurIPS 2020 Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

Finding the k largest or smallest elements from a collection of scores, i. e., top-k operation, is an important model component widely used in information retrieval, machine learning, and data mining.

Information Retrieval

A Simple Semi-Supervised Learning Framework for Object Detection

2 code implementations10 May 2020 Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, Tomas Pfister

Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.

Data Augmentation Image Classification +2

Differentiable Top-k Operator with Optimal Transport

no code implementations16 Feb 2020 Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

The top-k operation, i. e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.

Information Retrieval

Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

22 code implementations19 Dec 2019 Bryan Lim, Sercan O. Arik, Nicolas Loeff, Tomas Pfister

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i. e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target.

Interpretable Machine Learning Time Series +1

Distance-Based Learning from Errors for Confidence Calibration

no code implementations ICLR 2020 Chen Xing, Sercan Arik, Zizhao Zhang, Tomas Pfister

To circumvent this by inferring the distance for every test sample, we propose to train a confidence model jointly with the classification model.

Classification General Classification

On Completeness-aware Concept-Based Explanations in Deep Neural Networks

1 code implementation NeurIPS 2020 Chih-Kuan Yeh, Been Kim, Sercan O. Arik, Chun-Liang Li, Tomas Pfister, Pradeep Ravikumar

Next, we propose a concept discovery method that aims to infer a complete set of concepts that are additionally encouraged to be interpretable, which addresses the limitations of existing methods on concept explanations.

Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost

no code implementations ECCV 2020 Mingfei Gao, Zizhao Zhang, Guo Yu, Sercan O. Arik, Larry S. Davis, Tomas Pfister

Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance.

Active Learning Image Classification +1

Generative Modeling for Small-Data Object Detection

1 code implementation ICCV 2019 Lanlan Liu, Michael Muelly, Jia Deng, Tomas Pfister, Li-Jia Li

This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense.

Object Detection Pedestrian Detection +1

Distilling Effective Supervision from Severe Label Noise

2 code implementations CVPR 2020 Zizhao Zhang, Han Zhang, Sercan O. Arik, Honglak Lee, Tomas Pfister

For instance, on CIFAR100 with a $40\%$ uniform noise ratio and only 10 trusted labeled data per class, our method achieves $80. 2{\pm}0. 3\%$ classification accuracy, where the error rate is only $1. 4\%$ higher than a neural network trained without label noise.

Image Classification

RL-LIM: Reinforcement Learning-based Locally Interpretable Modeling

1 code implementation26 Sep 2019 Jinsung Yoon, Sercan O. Arik, Tomas Pfister

RL-LIM employs reinforcement learning to select a small number of samples and distill the black-box model prediction into a low-capacity locally interpretable model.

Data Valuation using Reinforcement Learning

1 code implementation ICML 2020 Jinsung Yoon, Sercan O. Arik, Tomas Pfister

To adaptively learn data values jointly with the target task predictor model, we propose a meta learning framework which we name Data Valuation using Reinforcement Learning (DVRL).

Domain Adaptation Meta-Learning

A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels

no code implementations20 Sep 2019 Yucen Luo, Jun Zhu, Tomas Pfister

Recently deep neural networks have shown their capacity to memorize training data, even with noisy labels, which hurts generalization performance.

Learning with noisy labels

Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning

no code implementations ECCV 2020 Linchao Zhu, Sercan O. Arik, Yi Yang, Tomas Pfister

We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset.

Transfer Learning

TabNet: Attentive Interpretable Tabular Learning

16 code implementations20 Aug 2019 Sercan O. Arik, Tomas Pfister

We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet.

Decision Making Feature Selection +3

Inserting Videos into Videos

no code implementations CVPR 2019 Donghoon Lee, Tomas Pfister, Ming-Hsuan Yang

To synthesize a realistic video, the network renders each frame based on the current input and previous frames.

Object Tracking Person Re-Identification

Harmonic Unpaired Image-to-image Translation

no code implementations ICLR 2019 Rui Zhang, Tomas Pfister, Jia Li

The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the presence of artifacts and degenerated transformations.

Image-to-Image Translation

ProtoAttend: Attention-Based Prototypical Learning

3 code implementations17 Feb 2019 Sercan O. Arik, Tomas Pfister

We propose a novel inherently interpretable machine learning method that bases decisions on few relevant examples that we call prototypes.

Decision Making General Classification +1

Personalizing Human Video Pose Estimation

no code implementations CVPR 2016 James Charles, Tomas Pfister, Derek Magee, David Hogg, Andrew Zisserman

The outcome is a substantial improvement in the pose estimates for the target video using the personalized ConvNet compared to the original generic ConvNet.

Optical Flow Estimation Pose Estimation

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