paper-with-me

홈 › Papers

SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels

2022-11-20 · Daehwan Kim, Kwangrok Ryoo, Hansang Cho, Seungryong Kim

Annotating the dataset with high-quality labels is crucial for performance of deep network, but in real world scenarios, the labels are often contaminated by noise. To address this, some methods were proposed to automatically split clean and noisy labels, and learn a semi-supervised learner in a Learning with Noisy Labels (LNL) framework. However, they leverage a handcrafted module for clean-noisy label splitting, which induces a confirmation bias in the semi-supervised learning phase and limits the performance. In this paper, we for the first time present a learnable module for clean-noisy label splitting, dubbed SplitNet, and a novel LNL framework which complementarily trains the SplitNet and main network for the LNL task. We propose to use a dynamic threshold based on a split confidence by SplitNet to better optimize semi-supervised learner. To enhance SplitNet training, we also present a risk hedging method. Our proposed method performs at a state-of-the-art level especially in high noise ratio settings on various LNL benchmarks.

📄 PDF Abstract BibTeX arXiv:2211.11753

Code (0)

등록된 구현이 없습니다.

Tasks

Learning with noisy labels

Similar Papers 제목 키워드 기반

SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems

2022-04-10 · CVPR 2022 1 · Xin Dong, Barbara De Salvo, Meng Li, Chiao Liu 외

We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in infer…

3D ClassificationDistributed ComputingNeural Architecture Search

Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learning

2025-10-11 · Bo Yuan, Yulin Chen, Yin Zhang arxiv

Parameter-efficient fine-tuning (PEFT) large language models (LLMs) have shown impressive performance in various downstream tasks. However, in many real-world scenarios, the collected training data inevitably contains no…

parameter-efficient fine-tuningText Classification

SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation

2019-05-18 · ICCV 2019 10 · Daniel Gordon, Abhishek Kadian, Devi Parikh, Judy Hoffman 외

We propose SplitNet, a method for decoupling visual perception and policy learning. By incorporating auxiliary tasks and selective learning of portions of the model, we explicitly decompose the learning objectives for vi…

Visual Navigation

Vision-Language Models are Strong Noisy Label Detectors

2024-09-29 · Tong Wei, Hao-Tian Li, Chun-Shu Li, Jiang-Xin Shi 외

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a si…

Denoisingimage-classificationImage Classificationparameter-efficient fine-tuning

Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels

2022-10-17 · Brandon Smart, Gustavo Carneiro

Many state-of-the-art noisy-label learning methods rely on learning mechanisms that estimate the samples' clean labels during training and discard their original noisy labels. However, this approach prevents the learning…

Image ClassificationLearning with noisy labels