Training Convolutional Networks with Noisy Labels
read the original abstract
The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e. there is some freely available label for each image which may or may not be accurate. In this paper, we explore the performance of discriminatively-trained Convnets when trained on such noisy data. We introduce an extra noise layer into the network which adapts the network outputs to match the noisy label distribution. The parameters of this noise layer can be estimated as part of the training process and involve simple modifications to current training infrastructures for deep networks. We demonstrate the approaches on several datasets, including large scale experiments on the ImageNet classification benchmark.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Silhouette Loss: Differentiable Global Structure Learning for Deep Representations
Soft Silhouette Loss offers a batch-global differentiable metric to promote intra-class compactness and inter-class separation in learned representations, boosting performance when hybridized with cross-entropy and co...
-
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning be...
-
Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook
LNMBench shows existing noisy-label methods degrade sharply under high and realistic noise in medical images due to class imbalance and domain shifts, and proposes a simple robustness fix.
-
FoodX-251: A Dataset for Fine-grained Food Classification
Introduces the FoodX-251 dataset of 251 food categories and 158k images to support fine-grained visual classification research and a related challenge.
-
Product Image Recognition with Guidance Learning and Noisy Supervision
Presents the Product-90 noisy product image dataset and a guidance learning method that combines noisy labels with teacher soft labels to train CNNs, reporting gains over prior methods on Product-90 and three public n...
-
Supervised Classifiers for Audio Impairments with Noisy Labels
CNNs generalize better than dense networks on noisy user labels for VoIP audio impairment classification, with larger datasets needed in proportion to noise level.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.