اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدتحسين المكانة الغير محددة يمكن أن تحسن المرونة ضد الضوضاء المسموحة بها للتسمية
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
526
0
0.0
(
0
)
اسأل ChatGPT حول البحث
تعلم مع تسميات مزعجة هو مشكلة تحديدية في التعلم المشروع بشكل ضعيف. في الأبحاث الحالية، يتم دائمًا النظر في الضوضاء المفتوحة كمسدسات للتعزيز، مماثلة للضوضاء المغلقة. في هذا البحث، نظرنا إلى أن التسميات المزعجة المفتوحة قد لا تكون سامة وأنها قد تساعد على المرونة ضد التسميات المزعجة الأصلية. مشحونين من هذه الملاحظات، نقترح تنظيمًا بسيطًا ولكن فعالًا عن طريق إدخال عينات مفتوحة مع تسميات مزعجة ديناميكية (ODNL) في التدريب. مع ODNL، يمكن استهلاك السعة الإضافية للشبكة العصبية بشكلٍ لا يتضرر من تعلم الأنماط من البيانات النظيفة. من خلال عدسة SGD noise، نظرنا إلى أن الضوضاء الناجمة عن طريقة عملنا هي عشوائية، خالية من الصراعات ومتحيزة، مما قد يساعد النموذج على التحقق من الحد الأدنى المستوي مع استقرار فائق وإجبار النموذج على إنتاج توقعات محايدة على المثال الخارج من التوزيع. يثبت النتائج التجريبية الشاملة على مجموعات بيانات المعيار مع أنواع مختلفة من التسميات المزعجة أن الطريقة المقترحة لا تحسن فقط أداء الخوارزميات المستقرة الموجودة، ولكنها تحقق تحسين كبير في مهام الكشف عن الخارج من التوزيع حتى في إعداد التسميات المزعجة.
Learning with noisy labels is a practically challenging problem in weakly supervised learning. In the existing literature, open-set noises are always considered to be poisonous for generalization, similar to closed-set noises. In this paper, we empirically show that open-set noisy labels can be non-toxic and even benefit the robustness against inherent noisy labels. Inspired by the observations, we propose a simple yet effective regularization by introducing Open-set samples with Dynamic Noisy Labels (ODNL) into training. With ODNL, the extra capacity of the neural network can be largely consumed in a way that does not interfere with learning patterns from clean data. Through the lens of SGD noise, we show that the noises induced by our method are random-direction, conflict-free and biased, which may help the model converge to a flat minimum with superior stability and enforce the model to produce conservative predictions on Out-of-Distribution instances. Extensive experimental results on benchmark datasets with various types of noisy labels demonstrate that the proposed method not only enhances the performance of many existing robust algorithms but also achieves significant improvement on Out-of-Distribution detection tasks even in the label noise setting.
قيم البحث
اقرأ أيضاً
Learning with the textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by decomposing them in
to parts. Annotators are therefore more likely to annotate instances based on the parts rather than the whole instances, where a wrong mapping from parts to classes may cause the instance-dependent label noise. Motivated by this human cognition, in this paper, we approximate the instance-dependent label noise by exploiting textit{part-dependent} label noise. Specifically, since instances can be approximately reconstructed by a combination of parts, we approximate the instance-dependent textit{transition matrix} for an instance by a combination of the transition matrices for the parts of the instance. The transition matrices for parts can be learned by exploiting anchor points (i.e., data points that belong to a specific class almost surely). Empirical evaluations on synthetic and real-world datasets demonstrate our method is superior to the state-of-the-art approaches for learning from the instance-dependent label noise.
Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. In this paper, we first de
rive analytical bound for any given noise patterns. Based on the insights, we design TrustNet that first adversely learns the pattern of noise corruption, being it both symmetric or asymmetric, from a small set of trusted data. Then, TrustNet is trained via a robust loss function, which weights the given labels against the inferred labels from the learned noise pattern. The weight is adjusted based on model uncertainty across training epochs. We evaluate TrustNet on synthetic label noise for CIFAR-10 and CIFAR-100, and real-world data with label noise, i.e., Clothing1M. We compare against state-of-the-art methods demonstrating the strong robustness of TrustNet under a diverse set of noise patterns.
Large datasets in NLP suffer from noisy labels, due to erroneous automatic and human annotation procedures. We study the problem of text classification with label noise, and aim to capture this noise through an auxiliary noise model over the classifi
er. We first assign a probability score to each training sample of having a noisy label, through a beta mixture model fitted on the losses at an early epoch of training. Then, we use this score to selectively guide the learning of the noise model and classifier. Our empirical evaluation on two text classification tasks shows that our approach can improve over the baseline accuracy, and prevent over-fitting to the noise.
Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a Multi-Objec
tive Interpolation Training (MOIT) approach that jointly exploits contrastive learning and classification to mutually help each other and boost performance against label noise. We show that standard supervised contrastive learning degrades in the presence of label noise and propose an interpolation training strategy to mitigate this behavior. We further propose a novel label noise detection method that exploits the robust feature representations learned via contrastive learning to estimate per-sample soft-labels whose disagreements with the original labels accurately identify noisy samples. This detection allows treating noisy samples as unlabeled and training a classifier in a semi-supervised manner to prevent noise memorization and improve representation learning. We further propose MOIT+, a refinement of MOIT by fine-tuning on detected clean samples. Hyperparameter and ablation studies verify the key components of our method. Experiments on synthetic and real-world noise benchmarks demonstrate that MOIT/MOIT+ achieves state-of-the-art results. Code is available at https://git.io/JI40X.
Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing methods suffer a lot from label noise. This paper targets at the challen
ge of robust training at high label noise regimes. The key insight to achieve this goal is to wisely leverage a small trusted set to estimate exemplar weights and pseudo labels for noisy data in order to reuse them for supervised training. We present a holistic framework to train deep neural networks in a way that is highly invulnerable to label noise. Our method sets the new state of the art on various types of label noise and achieves excellent performance on large-scale datasets with real-world label noise. For instance, on CIFAR100 with a $40%$ uniform noise ratio and only 10 trusted labeled data per class, our method achieves $80.2{pm}0.3%$ classification accuracy, where the error rate is only $1.4%$ higher than a neural network trained without label noise. Moreover, increasing the noise ratio to $80%$, our method still maintains a high accuracy of $75.5{pm}0.2%$, compared to the previous best accuracy $48.2%$. Source code available: https://github.com/google-research/google-research/tree/master/ieg
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
