Normalize Filters! Classical Wisdom for Deep Vision
Electrical Engineering and Computer Sciences, University of California, Berkeley（加州大学伯克利分校电子工程与计算机科学系）；Computer Science and Engineering, University of Michigan（密歇根大学计算机科学与工程系）
Classical image filters, such as those for averaging or differencing, are carefully normalized to ensure consistency, interpretability, and to avoid artifacts like intensity shifts, halos, or ringing. In contrast, convolutional filters learned end-to-end in deep networks lack such constraints. Although they may resemble wavelets and blob/edge detectors, they are not normalized in the same or any way. Consequently, when images undergo atmospheric transfer, their responses become distorted, leading to incorrect outcomes. We address this limitation by proposing filter normalization, followed by learnable scaling and shifting, akin to batch normalization. This simple yet effective modification ensures that the filters are atmosphere-equivariant, enabling co-domain symmetry. By integrating classical filtering principles into deep learning (applicable to both convolutional neural networks and convolution-dependent vision transformers), our method achieves significant improvements on artificial and natural intensity variation benchmarks. Our ResNet34 could even outperform CLIP by a large margin. Our analysis reveals that unnormalized filters degrade performance, whereas filter normalization regularizes learning, promotes diversity, and improves robustness and generalization.
Spectral graph theory is well known and widely used in computer vision. In this paper, we analyze image segmentation algorithms that are based on spectral graph theory, e.g., normalized cut, and show that there is a natural connection between spectural graph theory based image segmentationand and edge preserving filtering. Based on this connection we show that the normalized cut algorithm is equivalent to repeated iterations of bilateral filtering. Then, using this equivalence we present and implement a fast normalized cut algorithm for image segmentation. Experiments show that our implementat…
In this paper, we introduce a machine learning approach to the problem of infrared small target detection filter design. For this purpose, similarly to a convolutional layer of a neural network, the normalized-cross-correlational (NCC) layer, which we utilize for designing a target detection/recognition filter bank, is proposed. By employing the NCC layer in a neural network structure, we introduce a framework, in which supervised training is used to calculate the optimal filter shape and the optimum number of filters required for a specific target detection/recognition task on infrared images…
Band selection is a great challenging task in the classification of hyperspectral remotely sensed images HSI. This is resulting from its high spectral resolution, the many class outputs and the limited number of training samples. For this purpose, this paper introduces a new filter approach for dimension reduction and classification of hyperspectral images using information theoretic (normalized mutual information) and support vector machines SVM. This method consists to select a minimal subset of the most informative and relevant bands from the input datasets for better classification efficie…
Hong Kong Metropolitan University（香港都会大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Lingnan University（岭南大学）；Education University of Hong Kong（香港教育大学）
Image filters are fast, lightweight and effective, which make these conventional wisdoms preferable as basic tools in vision tasks. In practical scenarios, users have to tweak parameters multiple times to obtain satisfied results. This inconvenience heavily discounts the efficiency and user experience. We propose basis composition learning on single image filters to automatically determine their optimal formulas. The feasibility is based on a two-step strategy: first, we build a set of filtered basis (FB) consisting of approximations under selected parameter configurations; second, a dual-bran…
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息与电子工程学院）
Image registration is a fundamental issue in multispectral image processing. In filter wheel based multispectral imaging systems, the non-coplanar placement of the filters always causes the misalignment of multiple channel images. The selective characteristic of spectral response in multispectral imaging raises two challenges to image registration. First, the intensity levels of a local region may be different in individual channel images. Second, the local intensity may vary rapidly in some channel images while keeps stationary in others. Conventional multimodal measures, such as mutual infor…
Exact Consistency Tests for Gaussian Mixture Filters using Normalized Deviation Squared Statistics
Smead Aerospace Engineering Sciences, University of Colorado Boulder（科罗拉多大学博尔德分校斯米德航空航天工程科学学院）；Aurora Flight Sciences, a Boeing Company（波音公司旗下极光飞行科学公司）
We present a new approach for face recognition system. The method is based on 2D face image features using subset of non-correlated and Orthogonal Gabor Filters instead of using the whole Gabor Filter Bank, then compressing the output feature vector using Linear Discriminant Analysis (LDA). The face image has been enhanced using multi stage image processing technique to normalize it and compensate for illumination variation. Experimental results show that the proposed system is effective for both dimension reduction and good recognition performance when compared to the complete Gabor filter ba…
Template matching by normalized cross correlation (NCC) is widely used for finding image correspondences. We improve the robustness of this algorithm by preprocessing images with "siamese" convolutional networks trained to maximize the contrast between NCC values of true and false matches. The improvement is quantified using patches of brain images from serial section electron microscopy. Relative to a parameter-tuned bandpass filter, siamese convolutional networks significantly reduce false matches. Furthermore, all false matches can be eliminated by removing a tiny fraction of all matches ba…
Humboldt Universität Berlin（柏林洪堡大学）；Freie Universität Berlin（柏林自由大学）；Charité - Universitätsmedizin Berlin（柏林夏里特医学院）
Neuroimaging studies based on magnetic resonance imaging (MRI) typically employ rigorous forms of preprocessing. Images are spatially normalized to a standard template using linear and non-linear transformations. Thus, one can assume that a patch at location (x, y, height, width) contains the same brain region across the entire data set. Most analyses applied on brain MRI using convolutional neural networks (CNNs) ignore this distinction from natural images. Here, we suggest a new layer type called patch individual filter (PIF) layer, which trains higher-level filters locally as we assume that…
Hyperspectral images (HSI) classification is a high technical remote sensing tool. The main goal is to classify the point of a region. The HIS contains more than a hundred bidirectional measures, called bands (or simply images), of the same region called Ground Truth Map (GT). Unfortunately, some bands contain redundant information, others are affected by the noise, and the high dimensionalities of features make the accuracy of classification lower. All these bands can be important for some applications, but for the classification a small subset of these is relevant. In this paper we use mutua…
Target tracking in hyperspectral videos is a new research topic. In this paper, a novel method based on convolutional network and Kernelized Correlation Filter (KCF) framework is presented for tracking objects of interest in hyperspectral videos. We extract a set of normalized three-dimensional cubes from the target region as fixed convolution filters which contain spectral information surrounding a target. The feature maps generated by convolutional operations are combined to form a three-dimensional representation of an object, thereby providing effective encoding of local spectral-spatial i…
Many patch-based image denoising algorithms can be formulated as applying a smoothing filter to the noisy image. Expressed as matrices, the smoothing filters must be row normalized so that each row sums to unity. Surprisingly, if we apply a column normalization before the row normalization, the performance of the smoothing filter can often be significantly improved. Prior works showed that such performance gain is related to the Sinkhorn-Knopp balancing algorithm, an iterative procedure that symmetrizes a row-stochastic matrix to a doubly-stochastic matrix. However, a complete understanding of…
During the last decade, hyperspectral images have attracted increasing interest from researchers worldwide. They provide more detailed information about an observed area and allow an accurate target detection and precise discrimination of objects compared to classical RGB and multispectral images. Despite the great potentialities of hyperspectral technology, the analysis and exploitation of the large volume data remain a challenging task. The existence of irrelevant redundant and noisy images decreases the classification accuracy. As a result, dimensionality reduction is a mandatory step in or…
University of Bologna（博洛尼亚大学）；Datalogic S.r.l.（德利捷公司）
This work introduces a new framework, named SAFFIRE, to automatically extract a dominant recurrent image pattern from a set of image samples. Such a pattern shall be used to eliminate pose variations between samples, which is a common requirement in many computer vision and machine learning tasks. The framework is specialized here in the context of a machine vision system for automated product inspection. Here, it is customary to ask the user for the identification of an anchor pattern, to be used by the automated system to normalize data before further processing. Yet, this is a very sensitiv…
University of Maryland, College Park（马里兰大学帕克分校）；Gobasco AI Labs（戈巴斯科人工智能实验室）
We present an efficient foveal framework to perform object detection. A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales. Such a restriction of objects' size during training affords better learning of object-sensitive filters, and therefore, results in better accuracy. However, the use of an image pyramid increases the computational cost. Hence, we propose an efficient spatial sub-sampling scheme which only operates on fixed-size sub-regions likely to contain objects (as object locations are known …
Real-world image recognition is often challenged by the variability of visual styles including object textures, lighting conditions, filter effects, etc. Although these variations have been deemed to be implicitly handled by more training data and deeper networks, recent advances in image style transfer suggest that it is also possible to explicitly manipulate the style information. Extending this idea to general visual recognition problems, we present Batch-Instance Normalization (BIN) to explicitly normalize unnecessary styles from images. Considering certain style features play an essential…
Southwest Jiaotong University（西南交通大学）；Beijing Institute of Technology（北京理工学院）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing（测绘遥感信息工程国家重点实验室）
Co-registration of multimodal remote sensing images is still an ongoing challenge because of nonlinear radiometric differences (NRD) and significant geometric distortions (e.g., scale and rotation changes) between these images. In this paper, a robust matching method based on the Steerable filters is proposed consisting of two critical steps. First, to address severe NRD, a novel structural descriptor named the Steerable Filters of first- and second-Order Channels (SFOC) is constructed, which combines the first- and second-order gradient information by using the steerable filters with a multi-…
In this paper, we propose a deep snapshot high dynamic range (HDR) imaging framework that can effectively reconstruct an HDR image from the RAW data captured using a multi-exposure color filter array (ME-CFA), which consists of a mosaic pattern of RGB filters with different exposure levels. To effectively learn the HDR image reconstruction network, we introduce the idea of luminance normalization that simultaneously enables effective loss computation and input data normalization by considering relative local contrasts in the "normalized-by-luminance" HDR domain. This idea makes it possible to …
The University of Texas at El Paso（德克萨斯大学埃尔帕索分校）；Microsoft AI for Good Research Lab（微软益世AI研究实验室）；Georgia Institute of Technology（佐治亚理工学院）；Microsoft Research（微软研究院）
Normalization layers have been shown to improve convergence in deep neural networks, and even add useful inductive biases. In many vision applications the local spatial context of the features is important, but most common normalization schemes including Group Normalization (GN), Instance Normalization (IN), and Layer Normalization (LN) normalize over the entire spatial dimension of a feature. This can wash out important signals and degrade performance. For example, in applications that use satellite imagery, input images can be arbitrarily large; consequently, it is nonsensical to normalize o…
Neuroimaging data, e.g. obtained from magnetic resonance imaging (MRI), is comparably homogeneous due to (1) the uniform structure of the brain and (2) additional efforts to spatially normalize the data to a standard template using linear and non-linear transformations. Convolutional neural networks (CNNs), in contrast, have been specifically designed for highly heterogeneous data, such as natural images, by sliding convolutional filters over different positions in an image. Here, we suggest a new CNN architecture that combines the idea of hierarchical abstraction in neural networks with a pri…
Batch Normalization (BN) uses mini-batch statistics to normalize the activations during training, introducing dependence between mini-batch elements. This dependency can hurt the performance if the mini-batch size is too small, or if the elements are correlated. Several alternatives, such as Batch Renormalization and Group Normalization (GN), have been proposed to address this issue. However, they either do not match the performance of BN for large batches, or still exhibit degradation in performance for smaller batches, or introduce artificial constraints on the model architecture. In this pa…
