English
Related papers

Related papers: Mind the Pad -- CNNs can Develop Blind Spots

200 papers

This paper addresses a boosting method for mapping functionality of neural networks in visual recognition such as image classification and face recognition. We present reversible learning for generating and learning latent features using…

Machine Learning · Computer Science 2019-10-22 Jongmin Yu

How discriminative position information is for image classification depends on the data. On the one hand, the camera position is arbitrary and objects can appear anywhere in the image, arguing for translation invariance. At the same time,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Robert-Jan Bruintjes , Jan van Gemert

Compositional convolutional networks are generative compositional models of neural network features, that achieve state of the art results when classifying partially occluded objects, even when they have not been exposed to occluded objects…

Computer Vision and Pattern Recognition · Computer Science 2019-11-21 Adam Kortylewski , Qing Liu , Huiyu Wang , Zhishuai Zhang , Alan Yuille

Convolutional neural networks model the transformation of the input sensory data at the bottom of a network hierarchy to the semantic information at the top of the visual hierarchy. Feedforward processing is sufficient for some object…

Computer Vision and Pattern Recognition · Computer Science 2020-02-05 Mahdi Biparva , John Tsotsos

Visual attention brings significant progress for Convolution Neural Networks (CNNs) in various applications. In this paper, object-based attention in human visual cortex inspires us to introduce a mechanism for modification of activations…

Computer Vision and Pattern Recognition · Computer Science 2020-05-12 Saeed Masoudnia , Melika Kheirieh , Abdol-Hossein Vahabie , Babak Nadjar Araabi

Weakly supervised object localization is a challenging task in which the object of interest should be localized while learning its appearance. State-of-the-art methods recycle the architecture of a standard CNN by using the activation maps…

Computer Vision and Pattern Recognition · Computer Science 2020-12-03 Akhil Meethal , Marco Pedersoli , Soufiane Belharbi , Eric Granger

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural…

Computer Vision and Pattern Recognition · Computer Science 2018-11-29 Xizhou Zhu , Han Hu , Stephen Lin , Jifeng Dai

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yang Shen , Yusen Cai , Weronika Hryniewska-Guzik , Qing Lin , Mengmi Zhang

Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network…

Image and Video Processing · Electrical Eng. & Systems 2020-07-15 Meng Chang , Qi Li , Huajun Feng , Zhihai Xu

Neural networks often exhibit simplicity bias, favoring simpler features over more complex ones, even when both are equally predictive. We introduce a novel method called imbalanced label coupling to explore and extend this simplicity bias…

Machine Learning · Computer Science 2024-10-23 Zhehang Du

Humans are very good at directing their visual attention toward relevant areas when they search for different types of objects. For instance, when we search for cars, we will look at the streets, not at the top of buildings. The motivation…

Computer Vision and Pattern Recognition · Computer Science 2020-06-12 Hughes Perreault , Guillaume-Alexandre Bilodeau , Nicolas Saunier , Maguelonne Héritier

We discuss methods for visualizing neural network decision boundaries and decision regions. We use these visualizations to investigate issues related to reproducibility and generalization in neural network training. We observe that changes…

Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and analyze the network parameters, rather than inputs, which are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Roman Levin , Manli Shu , Eitan Borgnia , Furong Huang , Micah Goldblum , Tom Goldstein

Feature preference in Convolutional Neural Network (CNN) image classifiers is integral to their decision making process, and while the topic has been well studied, it is still not understood at a fundamental level. We test a range of task…

Computer Vision and Pattern Recognition · Computer Science 2022-01-25 Max Wolff , Stuart Wolff

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially…

Machine Learning · Computer Science 2018-06-05 Simon S. Du , Surbhi Goel

In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Shanshan Zhong , Wushao Wen , Jinghui Qin , Qiangpu Chen , Zhongzhan Huang

We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only identical loss curves but also…

Machine Learning · Computer Science 2023-12-07 Nikhil Vyas , Alexander Atanasov , Blake Bordelon , Depen Morwani , Sabarish Sainathan , Cengiz Pehlevan

Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features. These networks typically rely on a variety of regularization and pruning techniques to…

Computer Vision and Pattern Recognition · Computer Science 2017-10-23 Martin Mundt , Tobias Weis , Kishore Konda , Visvanathan Ramesh

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously…

Machine Learning · Computer Science 2022-01-19 Roman Pogodin , Yash Mehta , Timothy P. Lillicrap , Peter E. Latham

Due to limited size and imperfect of the optical components in a spectrometer, aberration has inevitably been brought into two-dimensional multi-fiber spectrum image in LAMOST, which leads to obvious spacial variation of the point spread…

Instrumentation and Methods for Astrophysics · Physics 2020-10-28 Jiali Xu , Qian Yin , Ping Guo , Xin Zheng