SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.00690 · ICML · 2022

From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model

Kyungwoo Song, Heesun Bae, Seungjae Shin, Byeonghu Na, Joonho Jang, Il-Chul Moon

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
BaeHeeSun/NPC — 3 of 7
debajyotid2/noisy_prediction_calibration — 3 of 6
FunctionStatusWhere it lives
CNN_CIFAR Ran debajyotid2/noisy_prediction_calibration/src/model.py
pointer only (licence: NONE) · get_code("4662422f1e547580")
ConvBlock Ran debajyotid2/noisy_prediction_calibration/src/model.py
pointer only (licence: NONE) · get_code("fe28cec2cd7f89f9")
DataIterator Ran BaeHeeSun/NPC/train_npc.py
code served (permissive licence) · get_code("82388716b0f85ec7")
food_dataset Ran BaeHeeSun/NPC/train_npc.py
code served (permissive licence) · get_code("31ad9bc4fd47fd15")
revised_dataset Ran BaeHeeSun/NPC/train_npc.py
code served (permissive licence) · get_code("6a560b8f68587e88")
softplus Ran debajyotid2/noisy_prediction_calibration/src/model.py
pointer only (licence: NONE) · get_code("71abe0c234120e1b")
CNN_MNIST Not yet run debajyotid2/noisy_prediction_calibration/src/model.py
pointer only (licence: NONE) · get_code("e5ea23e56cf9eb88")
CVAE Not yet run debajyotid2/noisy_prediction_calibration/src/model.py
pointer only (licence: NONE) · get_code("bfad4989b977aff9")
NPC Not yet run BaeHeeSun/NPC/train_npc.py
code served (permissive licence) · get_code("bfcfe8973219bd4f")
clothing_dataset Not yet run BaeHeeSun/NPC/train_npc.py
code served (permissive licence) · get_code("26a607b925ac39f3")
load_cnn Not yet run debajyotid2/noisy_prediction_calibration/src/model.py
pointer only (licence: NONE) · get_code("e32fce1e6402e49a")
load_dataset Not yet run BaeHeeSun/NPC/train_npc.py
code served (permissive licence) · get_code("4756d2ddfddd1ef2")
plot_ Not yet run BaeHeeSun/NPC/train_npc.py
code served (permissive licence) · get_code("04a2edcea2dabed9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Noisy labels are inevitable yet problematic in machine learning society. It ruins the generalization of a classifier by making the classifier over-fitted to noisy labels. Existing methods on noisy label have focused on modifying the classifier during the training procedure. It has two potential problems. First, these methods are not applicable to a pre-trained classifier without further access to training. Second, it is not easy to train a classifier and regularize all negative effects from noisy labels, simultaneously. We suggest a new branch of method, Noisy Prediction Calibration (NPC) in learning with noisy labels. Through the introduction and estimation of a new type of transition matrix via generative model, NPC corrects the noisy prediction from the pre-trained classifier to the true label as a post-processing scheme. We prove that NPC theoretically aligns with the transition matrix based methods. Yet, NPC empirically provides more accurate pathway to estimate true label, even without involvement in classifier learning. Also, NPC is applicable to any classifier trained with noisy label methods, if training instances and its predictions are available. Our method, NPC, boosts the classification performances of all baseline models on both synthetic and real-world datasets. The implemented code is available at https://github.com/BaeHeeSun/NPC.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2205.00690")
get_code_for_paper("2205.00690")
have("2205.00690")

Connect an agent — have() is free.