paperlist.ai

ICLR 2023 Papers

International Conference on Learning Representations

2026202520242023202220212020201920182017

Decision breakdown

1,575papers

Counted from the official paper list; may differ slightly from the number the conference announced.

  • Poster
    1,20476.4%
  • Other / unlabeled
    37123.6%

Top 10 topics (click to filter)

Trends for all 207 research topics

Browse all papers

All1,575Poster1,204
Learning to Segment from Noisy Annotations: A Spatial Correction Approach

Jiachen Yao, Yikai Zhang, Songzhu Zheng, Mayank Goswami, Prateek Prasanna, Chao Chen

Expand abstract

Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in annotation time and in the annotators' expertise. Existing methods mostly tackle label noise in classification tasks. Their independent-noise assumptions do not fit label noise in segmentation task. In this paper, we propose a novel noise model for segmentation problems that encodes spatial correlation and bias, which are prominent in segmentation annotations. Further, to mitigate such label noise, we propose a label correction method to recover true label progressively. We provide theoretical guarantees of the correctness of the proposed method. Experiments show that our approach outperforms current state-of-the-art methods on both synthetic and real-world noisy annotations.

Poster
Reinforcement LearningData Cleaning
Mitigating Memorization of Noisy Labels via Regularization between Representations

Hao Cheng, Zhaowei Zhu, Xing Sun, Yang Liu

Expand abstract

Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs). As a result, applying these losses may still suffer from overfitting/memorizing noisy labels as training proceeds. In this paper, we first theoretically analyze the memorization effect and show that a lower-capacity model may perform better on noisy datasets. However, it is non-trivial to design a neural network with the best capacity given an arbitrary task. To circumvent this dilemma, instead of changing the model architecture, we decouple DNNs into an encoder followed by a linear classifier and propose to restrict the function space of a DNN by a representation regularizer. Particularly, we require the distance between two self-supervised features to be positively related to the distance between the corresponding two supervised model outputs. Our proposed framework is easily extendable and can incorporate many other robust loss functions to further improve performance. Extensive experiments and theoretical analyses support our claims. Code is available at https://github.com/UCSC-REAL/SelfSup_NoisyLabel.

Poster
Deep learning · representation learningMulti-Task Learning