Search Results for author: Wan-Yi Lin

Found 12 papers, 2 papers with code

Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning

no code implementations14 Nov 2023 Xidong Wu, Wan-Yi Lin, Devin Willmott, Filipe Condessa, Yufei Huang, Zhenzhen Li, Madan Ravi Ganesh

Federated Learning (FL) is a distributed training paradigm that enables clients scattered across the world to cooperatively learn a global model without divulging confidential data.

Federated Learning

Text-driven Prompt Generation for Vision-Language Models in Federated Learning

no code implementations9 Oct 2023 Chen Qiu, Xingyu Li, Chaithanya Kumar Mummadi, Madan Ravi Ganesh, Zhenzhen Li, Lu Peng, Wan-Yi Lin

Prompt learning for vision-language models, e. g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons.

Federated Learning Image Classification

Defending Multimodal Fusion Models against Single-Source Adversaries

no code implementations CVPR 2021 Karren Yang, Wan-Yi Lin, Manash Barman, Filipe Condessa, Zico Kolter

Beyond achieving high performance across many vision tasks, multimodal models are expected to be robust to single-source faults due to the availability of redundant information between modalities.

Action Recognition object-detection +2

Empirical robustification of pre-trained classifiers

no code implementations ICML Workshop AML 2021 Mohammad Sadegh Norouzzadeh, Wan-Yi Lin, Leonid Boytsov, Leslie Rice, huan zhang, Filipe Condessa, J Zico Kolter

Most pre-trained classifiers, though they may work extremely well on the domain they were trained upon, are not trained in a robust fashion, and therefore are sensitive to adversarial attacks.

Denoising Image Reconstruction +1

Certified robustness against physically-realizable patch attack via randomized cropping

no code implementations1 Jan 2021 Wan-Yi Lin, Fatemeh Sheikholeslami, Jinghao Shi, Leslie Rice, J Zico Kolter

Our method improves upon the current state of the art in defending against patch attacks on CIFAR10 and ImageNet, both in terms of certified accuracy and inference time.

Classification Crop Classification +2

Crossing You in Style: Cross-modal Style Transfer from Music to Visual Arts

1 code implementation17 Sep 2020 Cheng-Che Lee, Wan-Yi Lin, Yen-Ting Shih, Pei-Yi Patricia Kuo, Li Su

Its major difference from the traditional image style transfer problem is that the style information is provided by music rather than images.

Generative Adversarial Network Style Transfer

Noisy Batch Active Learning with Deterministic Annealing

1 code implementation27 Sep 2019 Gaurav Gupta, Anit Kumar Sahu, Wan-Yi Lin

We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles.

Active Learning Clustering +2

Learning in Confusion: Batch Active Learning with Noisy Oracle

no code implementations25 Sep 2019 Gaurav Gupta, Anit Kumar Sahu, Wan-Yi Lin

We study the problem of training machine learning models incrementally using active learning with access to imperfect or noisy oracles.

Active Learning Denoising +1

DeepBbox: Accelerating Precise Ground Truth Generation for Autonomous Driving Datasets

no code implementations29 Aug 2019 Govind Rathore, Wan-Yi Lin, Ji Eun Kim

Autonomous driving requires various computer vision algorithms, such as object detection and tracking. Precisely-labeled datasets (i. e., objects are fully contained in bounding boxes with only a few extra pixels) are preferred for training such algorithms, so that the algorithms can detect exact locations of the objects.

Autonomous Driving Object +2

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