English
Related papers

Related papers: LIP: Local Importance-based Pooling

200 papers

Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the…

Computer Vision and Pattern Recognition · Computer Science 2019-06-26 Wenxiao Wang , Cong Fu , Jishun Guo , Deng Cai , Xiaofei He

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Computer Vision and Pattern Recognition · Computer Science 2025-05-08 Junjie Wang , Bin Chen , Yulin Li , Bin Kang , Yichi Chen , Zhuotao Tian

Pooling methods are necessities for modern neural networks for increasing receptive fields and lowering down computational costs. However, commonly used hand-crafted pooling approaches, e.g., max pooling and average pooling, may not well…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Lianyu Hu , Liqing Gao , Zekang Liu , Wei Feng

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Luqi Gong , Haotian Chen , Yikun Chen , Tianliang Yao , Chao Li , Shuai Zhao , Guangjie Han

Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of…

Computer Vision and Pattern Recognition · Computer Science 2014-09-10 Yunchao Gong , Liwei Wang , Ruiqi Guo , Svetlana Lazebnik

The inception network has been shown to provide good performance on image classification problems, but there are not much evidences that it is also effective for the image restoration or pixel-wise labeling problems. For image restoration…

Computer Vision and Pattern Recognition · Computer Science 2017-01-24 Yoonsik Kim , Insung Hwang , Nam Ik Cho

This paper studies co-segmenting the common semantic object in a set of images. Existing works either rely on carefully engineered networks to mine the implicit semantic information in visual features or require extra data (i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Xin Duan , Yan Yang , Liyuan Pan , Xiabi Liu

Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to…

Computer Vision and Pattern Recognition · Computer Science 2016-10-12 Miao Sun , Tony X. Han , Xun Xu , Ming-Chang Liu , Ahmad Khodayari-Rostamabad

Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision. Max-pooling purposefully discards precise spatial information in order to create…

Computer Vision and Pattern Recognition · Computer Science 2016-04-19 Sina Honari , Jason Yosinski , Pascal Vincent , Christopher Pal

In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that only retains the element with maximum activation, while completely discarding the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-17 Ashwani Kumar

Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational…

Computer Vision and Pattern Recognition · Computer Science 2015-06-10 Jonathan Tompson , Ross Goroshin , Arjun Jain , Yann LeCun , Christopher Bregler

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…

Computer Vision and Pattern Recognition · Computer Science 2014-12-02 George Papandreou , Iasonas Kokkinos , Pierre-André Savalle

The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling…

Computer Vision and Pattern Recognition · Computer Science 2019-04-26 Han Hu , Zheng Zhang , Zhenda Xie , Stephen Lin

Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-constrained platforms. While model compression techniques such…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Abhinav Shukla , Nachiket Tapas

Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions. Such pairwise functions underpin the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-08 Francesca Babiloni , Ioannis Marras , Filippos Kokkinos , Jiankang Deng , Grigorios Chrysos , Stefanos Zafeiriou

Images captured nowadays are of varying dimensions with smartphones and DSLR's allowing users to choose from a list of available image resolutions. It is therefore imperative for forensic algorithms such as resampling detection to scale…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Mohit Lamba , Kaushik Mitra

Efficient custom pooling techniques that can aggressively trim the dimensions of a feature map and thereby reduce inference compute and memory footprint for resource-constrained computer vision applications have recently gained significant…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Fang Chen , Gourav Datta , Souvik Kundu , Peter Beerel

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and…

Computer Vision and Pattern Recognition · Computer Science 2017-09-07 Dongyoon Han , Jiwhan Kim , Junmo Kim

In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Hao Zhang , Jianwei Ma

This paper concerns the use of objectness measures to improve the calibration performance of Convolutional Neural Networks (CNNs). CNNs have proven to be very good classifiers and generally localize objects well; however, the loss functions…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Ujwal Krothapalli , A. Lynn Abbott