English
Related papers

Related papers: Detail Preserving Residual Feature Pyramid Modules…

200 papers

We introduce Prior-Informed Flow Matching (PIFM), a conditional flow model for graph reconstruction. Reconstructing graphs from partial observations remains a key challenge; classical embedding methods often lack global consistency, while…

Machine Learning · Computer Science 2026-01-30 Harvey Chen , Nicolas Zilberstein , Santiago Segarra

The success of large-scale pre-trained models has established fine-tuning as a standard method for achieving significant improvements in downstream tasks. However, fine-tuning the entire parameter set of a pre-trained model is costly.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Yijin Huang , Pujin Cheng , Roger Tam , Xiaoying Tang

Prototype learning and decoder construction are the keys for few-shot segmentation. However, existing methods use only a single prototype generation mode, which can not cope with the intractable problem of objects with various scales.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Hongsheng Wang , Xiaoqi Zhao , Youwei Pang , Jinqing Qi

Video Frame Interpolation (VFI) is a crucial technique in various applications such as slow-motion generation, frame rate conversion, video frame restoration etc. This paper introduces an efficient video frame interpolation framework that…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Tong Shen , Dong Li , Ziheng Gao , Lu Tian , Emad Barsoum

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Salim Khazem , Ibrahim Mohamed Serouis , Zakaria Ezzahed

Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical tasks. The ReFlow procedure can accelerate sampling by…

Machine Learning · Computer Science 2024-10-11 Beomsu Kim , Yu-Guan Hsieh , Michal Klein , Marco Cuturi , Jong Chul Ye , Bahjat Kawar , James Thornton

Morphing is a long-standing problem in vision and computer graphics, requiring a time-dependent warping for feature alignment and a blending for smooth interpolation. Recently, multilayer perceptrons (MLPs) have been explored as implicit…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Arthur Bizzi , Matias Grynberg , Vitor Matias , Daniel Perazzo , João Paulo Lima , Luiz Velho , Nuno Gonçalves , João Pereira , Guilherme Schardong , Tiago Novello

LSTMs are powerful tools for modeling contextual information, as evidenced by their success at the task of language modeling. However, modeling contexts in very high dimensional space can lead to poor generalizability. We introduce the…

Computation and Language · Computer Science 2018-08-29 Sachin Mehta , Rik Koncel-Kedziorski , Mohammad Rastegari , Hannaneh Hajishirzi

Learning per-point semantic features from the hierarchical feature pyramid is essential for point cloud semantic segmentation. However, most previous methods suffered from ambiguous region features or failed to refine per-point features…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Peng Xiang , Xin Wen , Yu-Shen Liu , Hui Zhang , Yi Fang , Zhizhong Han

Recent advances in single image super-resolution (SISR) explored the power of convolutional neural network (CNN) to achieve a better performance. Despite the great success of CNN-based methods, it is not easy to apply these methods to edge…

Image and Video Processing · Electrical Eng. & Systems 2020-09-25 Jie Liu , Jie Tang , Gangshan Wu

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

Machine Learning · Computer Science 2025-07-01 Chengyu Dong , Huan Gui , Noveen Sachdeva , Long Jin , Ke Yin , Jingbo Shang , Lichan Hong , Ed H. Chi , Zhe Zhao

The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). While effective, these architectures are parameter-intensive…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Ange-Clément Akazan , Abdoulaye Koroko , Verlon Roel Mbingui , Choukouriyah Arinloye , Hassan Fifen , Rose Bandolo

The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Han Sun , Jun Cen , Ningzhong Liu , Dong Liang , Huiyu Zhou

Diffusion-based visuomotor policies excel at learning complex robotic tasks by effectively combining visual data with high-dimensional, multi-modal action distributions. However, diffusion models often suffer from slow inference due to…

Robotics · Computer Science 2025-08-08 Haoran Ding , Noémie Jaquier , Jan Peters , Leonel Rozo

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

Currently, low-resolution image recognition is confronted with a significant challenge in the field of intelligent traffic perception. Compared to high-resolution images, low-resolution images suffer from small size, low quality, and lack…

Computer Vision and Pattern Recognition · Computer Science 2023-09-29 Zongcai Tan , Zhenhai Gao

In computer vision most iterative optimization algorithms, both sparse and dense, rely on a coarse and reliable dense initialization to bootstrap their optimization procedure. For example, dense optical flow algorithms profit massively in…

Computer Vision and Pattern Recognition · Computer Science 2017-03-16 Matthias Ochs , Henry Bradler , Rudolf Mester

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive.…

Computer Vision and Pattern Recognition · Computer Science 2017-04-21 Tsung-Yi Lin , Piotr Dollár , Ross Girshick , Kaiming He , Bharath Hariharan , Serge Belongie

Semi-supervised video object segmentation (VOS) aims to segment a few moving objects in a video sequence, where these objects are specified by annotation of first frame. The optical flow has been considered in many existing semi-supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Ziyang Liu , Jingmeng Liu , Weihai Chen , Xingming Wu , Zhengguo Li