English
Related papers

Related papers: Improved Training Technique for Shortcut Models

200 papers

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Computation and Language · Computer Science 2025-12-24 Xiang Chen , Yixin Ou , Quan Feng , Lei Li , Piji Li , Haibo Ye , Sheng-Jun Huang , Shuofei Qiao , Shumin Deng , Huajun Chen , Ningyu Zhang

Conditional generative models, particularly diffusion-based methods, have recently been applied to graph prediction by modeling the target as a conditional distribution given the input graph, yielding competitive results compared to…

Artificial Intelligence · Computer Science 2026-05-08 Shaozhen Ma , Wei Huang , Hanchen Wang , Dong Wen , Wenjie Zhang

The superior performance of modern visual backbones usually comes with a costly training procedure. We contribute to this issue by generalizing the idea of curriculum learning beyond its original formulation, i.e., training models using…

Computer Vision and Pattern Recognition · Computer Science 2024-05-15 Yulin Wang , Yang Yue , Rui Lu , Yizeng Han , Shiji Song , Gao Huang

A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step alternatives are constrained by a hard quality ceiling. This…

Machine Learning · Computer Science 2025-09-05 Zidong Wang , Yiyuan Zhang , Xiaoyu Yue , Xiangyu Yue , Yangguang Li , Wanli Ouyang , Lei Bai

A primary challenge in semi-supervised learning (SSL) for segmentation is the confirmation bias from noisy pseudo-labels, which destabilizes training and degrades performance. We propose Inconsistency Masks (IM), a framework that reframes…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Michael R. H. Vorndran , Bernhard F. Roeck

Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent…

Machine Learning · Computer Science 2025-11-25 Chenrui Ma , Xi Xiao , Tianyang Wang , Xiao Wang , Yanning Shen

Learning with limited data is one of the biggest problems of machine learning. Current approaches to this issue consist in learning general representations from huge amounts of data before fine-tuning the model on a small dataset of…

Machine Learning · Computer Science 2023-02-22 Grégoire Mialon

Shortcut learning, i.e., a model's reliance on undesired features not directly relevant to the task, is a major challenge that severely limits the applications of machine learning algorithms, particularly when deploying them to assist in…

Machine Learning · Computer Science 2025-06-17 Lukas Kuhn , Sari Sadiya , Jorg Schlotterer , Florian Buettner , Christin Seifert , Gemma Roig

Training competitive deep video models is an order of magnitude slower than training their counterpart image models. Slow training causes long research cycles, which hinders progress in video understanding research. Following standard…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Chao-Yuan Wu , Ross Girshick , Kaiming He , Christoph Feichtenhofer , Philipp Krähenbühl

Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks. While recent research has explored the idea of…

Computation and Language · Computer Science 2023-05-25 Srijan Bansal , Semih Yavuz , Bo Pang , Meghana Bhat , Yingbo Zhou

Recent studies indicate that the denoising process in deep generative diffusion models implicitly learns and memorizes semantic information from the data distribution. These findings suggest that capturing more complex data distributions…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Yi Tang , Peng Sun , Zhenglin Cheng , Tao Lin

Despite the remarkable success of Self-Supervised Learning (SSL), its generalization is fundamentally hindered by Shortcut Learning, where models exploit superficial features like texture instead of intrinsic structure. We experimentally…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Siming Fu , Sijun Dong , Xiaoliang Meng

Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target dataset distribution. As a result, they capture only the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Zerun Wang , Jiafeng Mao , Xueting Wang , Toshihiko Yamasaki

Self-supervised approaches for video have shown impressive results in video understanding tasks. However, unlike early works that leverage temporal self-supervision, current state-of-the-art methods primarily rely on tasks from the image…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Ishan Rajendrakumar Dave , Simon Jenni , Mubarak Shah

Transductive few-shot learning has recently triggered wide attention in computer vision. Yet, current methods introduce key hyper-parameters, which control the prediction statistics of the test batches, such as the level of class balance,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Long Zhou , Fereshteh Shakeri , Aymen Sadraoui , Mounir Kaaniche , Jean-Christophe Pesquet , Ismail Ben Ayed

Consistency models (CMs) are a powerful class of diffusion-based generative models optimized for fast sampling. Most existing CMs are trained using discretized timesteps, which introduce additional hyperparameters and are prone to…

Machine Learning · Computer Science 2025-03-04 Cheng Lu , Yang Song

Few-shot segmentation focuses on the generalization of models to segment unseen object instances with limited training samples. Although tremendous improvements have been achieved, existing methods are still constrained by two factors. (1)…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Xianghui Yang , Bairun Wang , Kaige Chen , Xinchi Zhou , Shuai Yi , Wanli Ouyang , Luping Zhou

Current AI training infrastructure is dominated by single instruction multiple data (SIMD) and systolic array architectures, such as Graphics Processing Units (GPUs) and Tensor Processing Units (TPUs), that excel at accelerating parallel…

Neural and Evolutionary Computing · Computer Science 2023-11-09 Jan Finkbeiner , Thomas Gmeinder , Mark Pupilli , Alexander Titterton , Emre Neftci

The performance of deep segmentation models often degrades due to distribution shifts in image intensities between the training and test data sets. This is particularly pronounced in multi-centre studies involving data acquired using…

Image and Video Processing · Electrical Eng. & Systems 2021-08-03 Zhendong Liu , Van Manh , Xin Yang , Xiaoqiong Huang , Karim Lekadir , Víctor Campello , Nishant Ravikumar , Alejandro F Frangi , Dong Ni

Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This…

Machine Learning · Computer Science 2025-07-09 Michalis Korakakis , Andreas Vlachos , Adrian Weller