English
Related papers

Related papers: Complexity boosted adaptive training for better lo…

200 papers

An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as in Few-Shot Adaptation (FSA), data are insufficient…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Matteo Farina , Massimiliano Mancini , Giovanni Iacca , Elisa Ricci

Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenarios. Stabilizing online Test-Time Adaptation (TTA) under…

Sound · Computer Science 2024-10-08 Hongfu Liu , Hengguan Huang , Ye Wang

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Machine Learning · Computer Science 2025-12-15 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Shouhong Ding , Yuan Xie

Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between the negative maximum likelihood and the performance metric…

Computation and Language · Computer Science 2017-12-20 Yingbo Zhou , Caiming Xiong , Richard Socher

The deployment of multimodal models in high-stakes domains, such as self-driving vehicles and medical diagnostics, demands not only strong predictive performance but also reliable mechanisms for detecting failures. In this work, we address…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Moru Liu , Hao Dong , Olga Fink , Mario Trapp

Diffusion models have recently achieved remarkable success in generative modeling, yet their training dynamics across different noise levels remain highly imbalanced, which can lead to inefficient optimization and unstable learning…

Machine Learning · Computer Science 2026-03-12 Nanlong Sun , Lei Shi

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

Computation and Language · Computer Science 2025-03-13 Ahmed Adel Attia , Dorottya Demszky , Tolulope Ogunremi , Jing Liu , Carol Espy-Wilson

In computer vision, contrastive learning is the most advanced unsupervised learning framework. Yet most previous methods simply apply fixed composition of data augmentations to improve data efficiency, which ignores the changes in their…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Yuhan Zhang , He Zhu , Shan Yu

This paper addresses the observed performance gap between automatic speech recognition (ASR) systems based on Long Short Term Memory (LSTM) neural networks trained with the connectionist temporal classification (CTC) loss function and…

Computation and Language · Computer Science 2018-05-24 Jayadev Billa

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

Sound · Computer Science 2022-04-11 Nick J. C. Wang , Zongfeng Quan , Shaojun Wang , Jing Xiao

Point cloud datasets often suffer from inadequate sample sizes in comparison to image datasets, making data augmentation challenging. While traditional methods, like rigid transformations and scaling, have limited potential in increasing…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Jiacheng Wei , Guosheng Lin , Henghui Ding , Jie Hu , Kim-Hui Yap

Data augmentation is an effective technique to improve the generalization of deep neural networks. Recently, AutoAugment proposed a well-designed search space and a search algorithm that automatically finds augmentation policies in a…

Computer Vision and Pattern Recognition · Computer Science 2021-10-08 Chih-Yang Chen , Che-Han Chang

Airborne laser scanning (ALS) point cloud semantic segmentation is a fundamental task for large-scale 3D scene understanding. Fixed models deployed in real-world scenarios often suffer from performance degradation due to continuous domain…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Yuan Gao , Shaobo Xia , Sheng Nie , Cheng Wang , Xiaohuan Xi , Bisheng Yang

We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curriculum learning…

Artificial Intelligence · Computer Science 2026-02-20 Sumedh Rasal

Low-Rank Adaptation (LoRA) is the bread and butter of Large Language Model (LLM) finetuning. LoRA learns an additive low-rank perturbation, $AB$, of a pretrained matrix parameter $W$ to align the model to a new task or dataset with $W+AB$.…

Machine Learning · Computer Science 2024-10-15 Hai Huang , Randall Balestriero

While automatic speech recognition (ASR) systems degrade significantly in noisy environments, audio-visual speech recognition (AVSR) systems aim to complement the audio stream with noise-invariant visual cues and improve the system's…

Sound · Computer Science 2024-04-09 He Wang , Pengcheng Guo , Pan Zhou , Lei Xie

This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and making use of the duality between network weights and layer…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Lulan Shen , Ali Edalati , Brett Meyer , Warren Gross , James J. Clark

Varying data augmentation policies and regularization over the course of optimization has led to performance improvements over using fixed values. We show that population based training is a useful tool to continuously search those…

Computation and Language · Computer Science 2020-10-09 Daniel Haziza , Jérémy Rapin , Gabriel Synnaeve

In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-09 Yosuke Higuchi , Keita Karube , Tetsuji Ogawa , Tetsunori Kobayashi

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang