English
Related papers

Related papers: Efficient Feature Transformations for Discriminati…

200 papers

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

Machine Learning · Computer Science 2021-06-01 Sobirdzhon Bobiev , Adil Khan , Syed Muhammad Ahsan Raza Kazmi

Pretrained Foundation Models (PFMs) have transformed numerous applications by enabling efficient adaptation to customized tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a resource-efficient alternative to full fine-tuning,…

Machine Learning · Computer Science 2025-06-16 Baoquan Zhang , Guangning Xu , Michael. K. Ng

Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained…

Foundation models have significantly advanced medical image analysis through the pre-train fine-tune paradigm. Among various fine-tuning algorithms, Parameter-Efficient Fine-Tuning (PEFT) is increasingly utilized for knowledge transfer…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Raman Dutt , Linus Ericsson , Pedro Sanchez , Sotirios A. Tsaftaris , Timothy Hospedales

Gradient-based optimization has been a cornerstone of machine learning that enabled the vast advances of Artificial Intelligence (AI) development over the past decades. However, this type of optimization requires differentiation, and with…

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…

Machine Learning · Statistics 2025-07-09 Javan Tahir , Surya Ganguli , Grant M. Rotskoff

How do we transfer the relevant knowledge from ever larger foundation models into small, task-specific downstream models that can run at much lower costs? Standard transfer learning using pre-trained weights as the initialization transfers…

Machine Learning · Computer Science 2024-06-12 Shikai Qiu , Boran Han , Danielle C. Maddix , Shuai Zhang , Yuyang Wang , Andrew Gordon Wilson

Deep-learning density functional theory (DFT) shows great promise to significantly accelerate material discovery and potentially revolutionize materials research. However, current research in this field primarily relies on data-driven…

Computational Physics · Physics 2024-08-14 Yang Li , Zechen Tang , Zezhou Chen , Minghui Sun , Boheng Zhao , He Li , Honggeng Tao , Zilong Yuan , Wenhui Duan , Yong Xu

The emergence of large pre-trained networks has revolutionized the AI field, unlocking new possibilities and achieving unprecedented performance. However, these models inherit a fundamental limitation from traditional Machine Learning…

One of the main challenges in real-world reinforcement learning is to learn successfully from limited training samples. We show that in certain settings, the available data can be dramatically increased through a form of multi-task…

Machine Learning · Computer Science 2021-02-19 Desmond Cai , Shiau Hong Lim , Laura Wynter

Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Rui Zhao , Tianshan Liu , Jun Xiao , Daniel P. K. Lun , Kin-Man Lam

We consider the continual representation learning setting: sequentially pretrain a model $M'$ on tasks $T_1, \ldots, T_T$, and then adapt $M'$ on a small amount of data from each task $T_i$ to check if it has forgotten information from old…

Machine Learning · Computer Science 2023-02-28 Michael Sun , Ananya Kumar , Divyam Madaan , Percy Liang

Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Navid Eslami , Farnoosh Arefi , Amir M. Mansourian , Shohreh Kasaei

Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning…

Machine Learning · Computer Science 2024-11-05 Linglan Zhao , Xuerui Zhang , Ke Yan , Shouhong Ding , Weiran Huang

The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for input-adaptive…

Computation and Language · Computer Science 2025-10-16 Jan Miller

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…

Computer Vision and Pattern Recognition · Computer Science 2018-09-05 Francisco M. Castro , Manuel J. Marín-Jiménez , Nicolás Guil , Cordelia Schmid , Karteek Alahari

Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Zening Sun , Zhengpeng Xie , Lichen Bai , Shitong Shao , Shuo Yang , Zeke Xie

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Xinyuan Gao , Songlin Dong , Yuhang He , Xing Wei , Yihong Gong

Deep network architectures struggle to continually learn new tasks without forgetting the previous tasks. A recent trend indicates that dynamic architectures based on an expansion of the parameters can reduce catastrophic forgetting…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Arthur Douillard , Alexandre Ramé , Guillaume Couairon , Matthieu Cord