Related papers: Effect of Batch Normalization on Noise Resistant P…
Deep neural networks trained on large supervised datasets have led to impressive results in image classification and other tasks. However, well-annotated datasets can be time-consuming and expensive to collect, lending increased interest to…
The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems. However, the increasing depth of such models also results in a higher storage and…
The disparity between the computational demands of deep learning and the capabilities of compute hardware is expanding drastically. Although deep learning achieves remarkable performance in countless tasks, its escalating requirements for…
Humans tend to change their way of speaking when they are immersed in a noisy environment, a reflex known as Lombard effect. Current speech enhancement systems based on deep learning do not usually take into account this change in the…
The goal of this paper is to assess the impact of noise in 3D camera-captured data by modeling the noise of the imaging process and applying it on synthetic training data. We compiled a dataset of specifically constructed scenes to obtain a…
There is an emerging trend to leverage noisy image datasets in many visual recognition tasks. However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches. Recently, one mainstream is…
Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to improve both predictive performance and model calibration. In…
We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles. We select each batch of samples that are important and also diverse via clustering and importance sampling. More…
Normalization methods play an important role in enhancing the performance of deep learning while their theoretical understandings have been limited. To theoretically elucidate the effectiveness of normalization, we quantify the geometry of…
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize…
Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications.…
Adapting a model to perform well on unforeseen data outside its training set is a common problem that continues to motivate new approaches. We demonstrate that application of batch normalization in the output layer, prior to softmax…
Successful deep learning models often involve training neural network architectures that contain more parameters than the number of training samples. Such overparametrized models have been extensively studied in recent years, and the…
Magnetic Resonance Imaging (MRI) is considered the gold standard of medical imaging because of the excellent soft-tissue contrast exhibited in the images reconstructed by the MRI pipeline, which in-turn enables the human radiologist to…
Deep active learning has emerged as a powerful tool for training deep learning models within a predefined labeling budget. These models have achieved performances comparable to those trained in an offline setting. However, deep active…
We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to…
Deep convolutional networks often append additive constant ("bias") terms to their convolution operations, enabling a richer repertoire of functional mappings. Biases are also used to facilitate training, by subtracting mean response over…
Fourier embedding has shown great promise in removing spectral bias during neural network training. However, it can still suffer from high generalization errors, especially when the labels or measurements are noisy. We demonstrate that…
Normalization layers are critical components of modern AI systems, such as ChatGPT, Gemini, DeepSeek, etc. Empirically, they are known to stabilize training dynamics and improve generalization ability. However, the underlying theoretical…
Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is…