English
Related papers

Related papers: Modeling Selective Feature Attention for Represent…

200 papers

Combining several embeddings typically improves performance in downstream tasks as different embeddings encode different information. It has been shown that even models using embeddings from transformers still benefit from the inclusion of…

Computation and Language · Computer Science 2021-11-01 Lukas Lange , Heike Adel , Jannik Strötgen , Dietrich Klakow

Fine Grained Visual Categorization (FGVC) remains a challenging task in computer vision due to subtle inter class differences and fragile feature representations. Existing methods struggle in fine grained scenarios, especially when labeled…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Mingquan Liu

Convolutional neural networks (CNNs) have proven effective for image processing tasks, such as object recognition and classification. Recently, CNNs have been enhanced with concepts of attention, similar to those found in biology. Much of…

Computer Vision and Pattern Recognition · Computer Science 2015-12-10 Grace W. Lindsay

Learning latent features from time series data is an important problem in both machine learning and brain function. One approach, called Slow Feature Analysis (SFA), leverages the slowness of many salient features relative to the rapidly…

Neurons and Cognition · Quantitative Biology 2020-10-27 David Lipshutz , Charlie Windolf , Siavash Golkar , Dmitri B. Chklovskii

When some application scenarios need to use semantic segmentation technology, like automatic driving, the primary concern comes to real-time performance rather than extremely high segmentation accuracy. To achieve a good trade-off between…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Liang Liao , Liang Wan , Mingsheng Liu , Shusheng Li

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…

Computation and Language · Computer Science 2026-03-27 Yijiong Yu , Jiale Liu , Qingyun Wu , Huazheng Wang , Ji Pei

Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are proven to be effective due to their ability to form…

Robotics · Computer Science 2022-09-28 Alper Ahmetoglu , Emre Ugur , Minoru Asada , Erhan Oztop

Irrelevant features can significantly degrade few-shot learn ing performance. This problem is used to match queries and support images based on meaningful similarities despite the limited data. However, in this process, non-relevant fea…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Javier Rodenas , Eduardo Aguilar , Petia Radeva

In this paper, we propose an end-to-end feature fusion at-tention network (FFA-Net) to directly restore the haze-free image. The FFA-Net architecture consists of three key components: 1) A novel Feature Attention (FA) module combines…

Computer Vision and Pattern Recognition · Computer Science 2019-12-06 Xu Qin , Zhilin Wang , Yuanchao Bai , Xiaodong Xie , Huizhu Jia

Existing deep learning approaches leave out the semantic cues that are crucial in semantic segmentation present in complex scenarios including cluttered backgrounds and translucent objects, etc. To handle these challenges, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Muhammad Ali , Mamoona Javaid , Mubashir Noman , Mustansar Fiaz , Salman Khan

Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods…

Machine Learning · Computer Science 2024-02-20 Moritz Lange , Raphael C. Engelhardt , Wolfgang Konen , Laurenz Wiskott

Motion, as the uniqueness of a video, has been critical to the development of video understanding models. Modern deep learning models leverage motion by either executing spatio-temporal 3D convolutions, factorizing 3D convolutions into…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Fuchen Long , Zhaofan Qiu , Yingwei Pan , Ting Yao , Jiebo Luo , Tao Mei

Feature selection is an important process in machine learning. It builds an interpretable and robust model by selecting the features that contribute the most to the prediction target. However, most mature feature selection algorithms,…

Machine Learning · Computer Science 2022-07-20 Zhifeng Qiu , Wanxin Zeng , Dahua Liao , Ning Gui

Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in…

Computer Vision and Pattern Recognition · Computer Science 2019-07-17 Zhang Zhang , Dacheng Tao

The attention mechanism has been proven to be an effective way to improve spiking neural network (SNN). However, based on the fact that the current SNN input data flow is split into tensors to process on GPUs, none of the previous works…

Machine Learning · Computer Science 2024-04-12 Haoyu Deng , Ruijie Zhu , Xuerui Qiu , Yule Duan , Malu Zhang , Liangjian Deng

While recent semantic segmentation networks heavily rely on powerful pretrained encoders, most employ simplistic decoders, leading to suboptimal trade-offs between semantic context and fine-grained detail preservation. To address this, we…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Guoan Xu , Yang Xiao , Wenjing Jia , Guangwei Gao , Guo-Jun Qi , Chia-Wen Lin

Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches typically ignore the…

Computation and Language · Computer Science 2025-12-01 Dayan Pan , Jingyuan Wang , Yilong Zhou , Jiawei Cheng , Pengyue Jia , Xiangyu Zhao

The self-attention mechanism is the backbone of the transformer neural network underlying most large language models. It can capture complex word patterns and long-range dependencies in natural language. This paper introduces exponential…

Machine Learning · Statistics 2025-01-29 Kevin Christian Wibisono , Yixin Wang

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

Information Retrieval · Computer Science 2022-05-19 Mohan Hasama , Jing Li

Feature selection is essential for high-dimensional biomedical data, enabling stronger predictive performance, reduced computational cost, and improved interpretability in precision medicine applications. Existing approaches face notable…

Machine Learning · Computer Science 2026-01-07 Xiaoyan Sun , Qingyu Meng , Yalu Wen