Related papers: Gradient Harmonized Single-stage Detector

This paper proposes a hybrid approach for co-channel speech segregation. HMM (hidden Markov model) is used to track the pitches of 2 talkers. The resulting pitch tracks are then enriched with the prominent pitch. The enriched tracks are…

Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…

Many speech and music analysis and processing schemes rely on an estimate of the fundamental frequency $f_0$ of periodic signal components. Most established schemes apply rather unspecific signal models such as sinusoidal models to the…

With the continuous improvement of the performance of object detectors via advanced model architectures, imbalance problems in the training process have received more attention. It is a common paradigm in object detection frameworks to…

Deep Learning (DL) methods show very good performance when trained on large, balanced data sets. However, many practical problems involve imbalanced data sets, or/and classes with a small number of training samples. The performance of DL…

We propose a new metric ($m$-coherence) to experimentally study the alignment of per-example gradients during training. Intuitively, given a sample of size $m$, $m$-coherence is the number of examples in the sample that benefit from a small…

We focus on the classification problem with a separable dataset, one of the most important and classical problems from machine learning. The standard approach to this task is logistic regression with gradient descent (LR+GD). Recent studies…

Current Point-based detectors can only learn from the provided points, with limited receptive fields and insufficient global learning capabilities for such targets. In this paper, we present a novel Point Dilation Mechanism for single-stage…

Sensor-based Human Activity Recognition (HAR) is a core technology that enables intelligent systems to perceive and interact with their environment. However, multimodal HAR systems still encounter key challenges, such as difficulties in…

Most Multimodal Sentiment Analysis research has focused on point-wise regression. While straightforward, this approach is sensitive to label noise and neglects whether one sample is more positive than another, resulting in unstable…

Deep neural networks designed for vision tasks are often prone to failure when they encounter environmental conditions not covered by the training data. Single-modal strategies are insufficient when the sensor fails to acquire information…

Prompt engineering is crucial for fully leveraging large language models (LLMs), yet most existing optimization methods follow a single trajectory, resulting in limited adaptability, gradient conflicts, and high computational overhead. We…

We develop subgradient- and gradient-based methods for minimizing strongly convex functions under a notion which generalizes the standard Euclidean strong convexity. We propose a unifying framework for subgradient methods which yields two…

Object detection has been a challenging task in computer vision. Although significant progress has been made in object detection with deep neural networks, the attention mechanism is far from development. In this paper, we propose the…

We propose a communication-efficient optimally structured gradient coding scheme to jointly address straggler resilience and communication efficiency in heterogeneous distributed learning. By establishing a unified framework that…

Learning precise Boolean logic via gradient descent remains challenging: neural networks typically converge to "fuzzy" approximations that degrade under quantization. We introduce Hierarchical Spectral Composition, a differentiable…

Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-the-art performance on a variety of machine learning tasks. Several researchers have recently proposed schemes to parallelize SGD, but all require…

Various gradient compression schemes have been proposed to mitigate the communication cost in distributed training of large scale machine learning models. Sign-based methods, such as signSGD, have recently been gaining popularity because of…

This contribution presents the design, production, and initial testing of newly developed 4H-SiC Low Gain Avalanche Detectors (LGADs). The evaluation includes performance metrics such as the internal gain layer's efficiency in enhancing…

Hallucinations in Large Language Models (LLMs) pose a significant challenge, generating misleading or unverifiable content that undermines trust and reliability. Existing evaluation methods, such as KnowHalu, employ multi-stage verification…