English
Related papers

Related papers: Mean Box Pooling: A Rich Image Representation and …

200 papers

Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger…

Computer Vision and Pattern Recognition · Computer Science 2014-12-30 Wei Yu , Kuiyuan Yang , Yalong Bai , Hongxun Yao , Yong Rui

In this paper, we investigate the problems that Convolutional Neural Networks (CNN)-based pose estimators have with symmetric objects. We considered the value of the CNN's output representation when continuously rotating the object and…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Jesse Richter-Klug , Udo Frese

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic…

Computer Vision and Pattern Recognition · Computer Science 2017-04-11 Samuel Rota Bulò , Gerhard Neuhold , Peter Kontschieder

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of…

Computation and Language · Computer Science 2023-01-10 Zhuosheng Zhang , Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita , Zuchao Li , Hai Zhao

This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional neural network (CNN). The method heavily hinges on exploring…

Computer Vision and Pattern Recognition · Computer Science 2017-05-23 Mariusz Bojarski , Anna Choromanska , Krzysztof Choromanski , Bernhard Firner , Larry Jackel , Urs Muller , Karol Zieba

Deep convolutional neural networks provide a powerful feature learning capability for image classification. The deep image features can be utilized to deal with many image understanding tasks like image classification and object…

Computer Vision and Pattern Recognition · Computer Science 2018-11-20 Shaoning Zeng , Bob Zhang , Yanghao Zhang , Jianping Gou

Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks. However, they are becoming increasingly larger, using millions of parameters,…

Computer Vision and Pattern Recognition · Computer Science 2017-07-27 Nikolaos Passalis , Anastasios Tefas

Modern convolutional neural networks (CNNs)-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further…

Computer Vision and Pattern Recognition · Computer Science 2022-07-25 Shi Luo , Xiongfei Li , Xiaoli Zhang

A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Xin Liu , Zhongdao Wang , Yali Li , Shengjin Wang

Deep learning methods have revolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial…

Artificial Intelligence · Computer Science 2020-07-15 Chao Zhang , Zichao Yang , Xiaodong He , Li Deng

Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical image analysis or self-driving cars, confirmability is…

Computer Vision and Pattern Recognition · Computer Science 2018-01-08 Keyang Zhou , Bernhard Kainz

Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answering this question, we…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Junjie Hu , Yan Zhang , Takayuki Okatani

By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant…

Machine Learning · Computer Science 2024-07-24 Hiroyuki Tokunaga , Joel Nicholls , Daria Vazhenina , Atsunori Kanemura

Deep convolutional networks have recently shown excellent performance on Fine-Grained Vehicle Classification. Based on these existing works, we consider that the back-probation algorithm does not focus on extracting less discriminative…

Computer Vision and Pattern Recognition · Computer Science 2020-01-28 Zhanyu Ma , Dongliang Chang , Xiaoxu Li

Recent multi-view subspace clustering achieves impressive results utilizing deep networks, where the self-expressive correlation is typically modeled by a fully connected (FC) layer. However, they still suffer from two limitations. i) The…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Yuxiu Lin , Hui Liu , Ren Wang , Qiang Guo , Caiming Zhang

We propose Context-Adaptive Multi-Prompt Embedding, a novel approach to enrich semantic representations in vision-language contrastive learning. Unlike standard CLIP-style models that rely on a single text embedding, our method introduces…

Machine Learning · Computer Science 2025-08-07 Dahun Kim , Anelia Angelova

Discrete Fourier transforms provide a significant speedup in the computation of convolutions in deep learning. In this work, we demonstrate that, beyond its advantages for efficient computation, the spectral domain also provides a powerful…

Machine Learning · Statistics 2015-06-12 Oren Rippel , Jasper Snoek , Ryan P. Adams

The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification. Systematically, we study three facts in CNN transfer. 1) We demonstrate the advantage of using…

Computer Vision and Pattern Recognition · Computer Science 2016-04-04 Liang Zheng , Yali Zhao , Shengjin Wang , Jingdong Wang , Qi Tian

Image splicing is a very common image manipulation technique that is sometimes used for malicious purposes. A splicing detec- tion and localization algorithm usually takes an input image and produces a binary decision indicating whether the…

Computer Vision and Pattern Recognition · Computer Science 2017-05-30 Yue Wu , Wael AbdAlmageed , Prem Natarajan

We introduce a deep multitask architecture to integrate multityped representations of multimodal objects. This multitype exposition is less abstract than the multimodal characterization, but more machine-friendly, and thus is more precise…

Machine Learning · Statistics 2016-03-07 Truyen Tran , Dinh Phung , Svetha Venkatesh