In this study, we introduce an enhanced version of ViT that conducts attention-based QKV operations during the initial stages of downsampling. Performing attention directly on high-resolution feature maps is computationally demanding due to the large size and numerous tokens. To mitigate this, we propose a filter attention mechanism that uses a Filter Block to create a salient mask (Filter Mask) for selecting the most informative pixels for attention.
The Filter Block scores the pixels of the feature map, and we sort these scores to retain only the top K pixels (with K varying across layers). This approach effectively decreases the number of tokens involved in the attention computation, reducing computational complexity and boosting processing speed. Furthermore, the salient mask provides interpretability, as the model focuses on regions of the image most critical to the outcome.
Our experimental results show that this model improves parameter efficiency and computational speed while enhancing accuracy. Compared to existing models, our approach significantly reduces resource consumption while maintaining high performance.
Referring image segmentation aims at localizing all pixels of the visual objects described by a natural language sentence. Previous works learn to straightforwardly align the sentence embedding and pixel-level embedding for highlighting the referred objects, but ignore the semantic consistency of pixels within the same object, leading to incomplete masks and localization errors in predictions. To tackle this problem, we propose CoupAlign, a simple yet effective multi-level visual-semantic alignment method, to couple sentence-mask alignment with word-pixel alignment to enforce object mask const…
Facebook AI Research（Facebook人工智能研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. Overall, the proposed mask class…
Affectiva（Affectiva公司）；University of Notre Dame（圣母大学）
We propose a multi-scale GAN model to hallucinate realistic context (forehead, hair, neck, clothes) and background pixels automatically from a single input face mask. Instead of swapping a face on to an existing picture, our model directly generates realistic context and background pixels based on the features of the provided face mask. Unlike face inpainting algorithms, it can generate realistic hallucinations even for a large number of missing pixels. Our model is composed of a cascaded network of GAN blocks, each tasked with hallucination of missing pixels at a particular resolution while g…
Hangzhou Dianzi University（杭州电子科技大学）；Zhejiang International Studies University（浙江外国语学院）；University of Sydney（悉尼大学）
Object instance segmentation is one of the most fundamental but challenging tasks in computer vision, and it requires the pixel-level image understanding. Most existing approaches address this problem by adding a mask prediction branch to a two-stage object detector with the Region Proposal Network (RPN). Although producing good segmentation results, the efficiency of these two-stage approaches is far from satisfactory, restricting their applicability in practice. In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pix…
MaskCD: A Remote Sensing Change Detection Network Based on Mask Classification
Helmholtz Institute Freiberg for Resource Technology（弗莱贝格亥姆霍兹资源技术研究所）；Helmholtz-Zentrum Dresden-Rossendorf（德累斯顿-罗森多夫亥姆霍兹中心）；Technical University of Munich (TUM)（慕尼黑工业大学）；School of Information Science and Engineering, Wuhan University of Science and Technology（武汉科技大学信息科学与工程学院）；School of Engineering, Shiv Nadar University（希夫·纳达尔大学工程学院）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Lancaster University（兰卡斯特大学）
Princeton University（普林斯顿大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
We introduce Mask-ToF, a method to reduce flying pixels (FP) in time-of-flight (ToF) depth captures. FPs are pervasive artifacts which occur around depth edges, where light paths from both an object and its background are integrated over the aperture. This light mixes at a sensor pixel to produce erroneous depth estimates, which can adversely affect downstream 3D vision tasks. Mask-ToF starts at the source of these FPs, learning a microlens-level occlusion mask which effectively creates a custom-shaped sub-aperture for each sensor pixel. This modulates the selection of foreground and backgroun…
Mask-HybridGNet: Graph-based segmentation with emergent anatomical correspondence from pixel-level supervision
Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain（生物医学影像技术，电信工程学院，马德里理工大学，马德里，西班牙）；IHU PRISM National Precision Medicine Center in Oncology, Cancer Data Science Unit, CentraleSupélec, Gustave Roussy, INSERM, Université Paris-Saclay, Gif-sur-Yvette, France（IHU PRISM国家精准医学中心（肿瘤学），癌症数据科学单元，中央圣艾尔布兰，格斯塔夫·罗西，国家医学研究所，巴黎-萨克雷大学，法国）
Point-to-Mask: From Arbitrary Point Annotations to Mask-Level Infrared Small Target Detection
Key Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences（空间系统电子信息技术重点实验室，国家空间科学中心，中国科学院）
Informatics Institute of the University of Amsterdam（阿姆斯特丹大学信息学研究所）
The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering by means of an additional guidance image. Where classical guided filters transfer structures using hand-designed functions, recent guided filters have been considerably advanced through parametric learning of deep networks. The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter. In this work, we posit that simultaneously estimating both coefficients is suboptimal, resulting in halo artifacts and structure inconsistencies. Insp…
Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. …
We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer architectures used in segmentation and detection; CMT-DeepLab considers the object queries as cluster centers, which fill the role of grouping the pixels when applied to segmentation. The clustering is computed with an alternating procedure, by first assigning pixels to the clusters by their feature affinity, and then updating the cluster centers and pixel features. Together, these operations comprise the Clustering Mask …
Applying feature dependent network weights have been proved to be effective in many fields. However, in practice, restricted by the enormous size of model parameters and memory footprints, scalable and versatile dynamic convolutions with per-pixel adapted filters are yet to be fully explored. In this paper, we address this challenge by decomposing filters, adapted to each spatial position, over dynamic filter atoms generated by a light-weight network from local features. Adaptive receptive fields can be supported by further representing each filter atom over sets of pre-fixed multi-scale bases…
What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks
Jagiellonian University（雅盖隆大学）；University of Information Technology and Management in Rzeszów（热舒夫信息技术与管理大学）；Jagiellonian University Medical College（雅盖隆大学医学院）
The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；University of Science and Technology of China（中国科学技术大学）；Peking University（北京大学）
Distilling from the feature maps can be fairly effective for dense prediction tasks since both the feature discriminability and localization priors can be well transferred. However, not every pixel contributes equally to the performance, and a good student should learn from what really matters to the teacher. In this paper, we introduce a learnable embedding dubbed receptive token to localize those pixels of interests (PoIs) in the feature map, with a distillation mask generated via pixel-wise attention. Then the distillation will be performed on the mask via pixel-wise reconstruction. In this…
Recently, significant progress has been achieved in deep image matting. Most of the classical image matting methods are time-consuming and require an ideal trimap which is difficult to attain in practice. A high efficient image matting method based on a weakly annotated mask is in demand for mobile applications. In this paper, we propose a novel method based on Deep Learning and Guided Filter, called Inductive Guided Filter, which can tackle the real-time general image matting task on mobile devices. We design a lightweight hourglass network to parameterize the original Guided Filter method th…
Deep neural networks have achieved satisfactory performance in piles of medical image analysis tasks. However the training of deep neural network requires a large amount of samples with high-quality annotations. In medical image segmentation, it is very laborious and expensive to acquire precise pixel-level annotations. Aiming at training deep segmentation models on datasets with probably corrupted annotations, we propose a novel Meta Corrupted Pixels Mining (MCPM) method based on a simple meta mask network. Our method is targeted at automatically estimate a weighting map to evaluate the impor…
Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学）；Tencent Youtu Lab（腾讯云视频实验室）
This paper introduces a new approach to non-local means image denoising. Instead of using all pixels located in the search window for estimating the value of a pixel, we identify the highly corrupted pixels and assign less weight to these pixels. This method is called robust non-local means. Numerical and subjective evaluations using ultrasound images show good performances of the proposed denoising method in recovering the shape of edges and important detailed components, in comparison to traditional ultrasound image denoising methods
Kalyani University（卡利亚尼大学）；The University of Burdwan（布尔德万大学）
The most median-based de noising methods works fine for restoring the images corrupted by Randomn Valued Impulse Noise with low noise level but very poor with highly corrupted images. In this paper a directional weighted minimum deviation (DWMD) based filter has been proposed for removal of high random valued impulse noise (RVIN). The proposed approach based on Standard Deviation (SD) works in two phases. The first phase detects the contaminated pixels by differencing between the test pixel and its neighbor pixels aligned with four main directions. The second phase filters only those pixels ke…
Korea University（高丽大学）；Chungbuk National University Hospital（忠北国立大学医院）；Hannam University（韩南大学）
Region-adaptive normalization (RAN) methods have been widely used in the generative adversarial network (GAN)-based image-to-image translation technique. However, since these approaches need a mask image to infer the pixel-wise affine transformation parameters, they cannot be applied to the general image generation models having no paired mask images. To resolve this problem, this paper presents a novel normalization method, called self pixel-wise normalization (SPN), which effectively boosts the generative performance by performing the pixel-adaptive affine transformation without the mask ima…
Zhejiang University（浙江大学）；Huazhong University of Science and Technology（华中科技大学）；Tencent Youtu Lab（腾讯优图实验室）
Current instance segmentation methods can be categorized into segmentation-based methods that segment first then do clustering, and proposal-based methods that detect first then predict masks for each instance proposal using repooling. In this work, we propose a one-stage method, named EmbedMask, that unifies both methods by taking advantages of them. Like proposal-based methods, EmbedMask builds on top of detection models making it strong in detection capability. Meanwhile, EmbedMask applies extra embedding modules to generate embeddings for pixels and proposals, where pixel embeddings are gu…
Image denoising is a critical issue in the field of digital image processing. This paper proposes a novel Salt & Pepper noise suppression by developing a Kriging Interpolation Filter (KIF) for image denoising. Gray-level images degraded with Salt & Pepper noise have been considered. A sequential search for noise detection was made using kXk window size to determine non-noisy pixels only. The non-noisy pixels are passed into Kriging interpolation method to predict their absent neighbor pixels that were noisy pixels at the first phase. The utilization of Kriging interpolation filter proves that …
Weakly supervised object localization (WSOL) is a challenging task to localize the object by only category labels. However, there is contradiction between classification and localization because accurate classification network tends to pay attention to discriminative region of objects rather than the entirety. We propose this discrimination is caused by handcraft threshold choosing in CAM-based methods. Therefore, we propose Clustering and Filter of Tokens (CaFT) with Vision Transformer (ViT) backbone to solve this problem in another way. CaFT first sends the patch tokens of the image split to…
Few-shot semantic segmentation aims to recognize novel classes with only very few labelled data. This challenging task requires mining of the relevant relationships between the query image and the support images. Previous works have typically regarded it as a pixel-wise classification problem. Therefore, various models have been designed to explore the correlation of pixels between the query image and the support images. However, they focus only on pixel-wise correspondence and ignore the overall correlation of objects. In this paper, we introduce a mask-based classification method for address…
Tel Aviv University（特拉维夫大学）；Bar-Ilan University（巴伊兰大学）
This paper explores the use of a soft ground-truth mask ("soft mask'') to train a Fully Convolutional Neural Network (FCNN) for segmentation of Multiple Sclerosis (MS) lesions. Detection and segmentation of MS lesions is a complex task largely due to the extreme unbalanced data, with very small number of lesion pixels that can be used for training. Utilizing the anatomical knowledge that the lesion surrounding pixels may also include some lesion level information, we suggest to increase the data set of the lesion class with neighboring pixel data - with a reduced confidence weight. A soft mask…
This work examines the use of a fully convolutional net (FCN) to find an image segment, given a pixel within this segment region. The net receives an image, a point in the image and a region of interest (RoI ) mask. The net output is a binary mask of the segment in which the point is located. The region where the segment can be found is contained within the input RoI mask. Full image segmentation can be achieved by running this net sequentially, region-by-region on the image, and stitching the output segments into a single segmentation map. This simple method addresses two major challenges of …
Georgia Institute of Technology（佐治亚理工学院）；Apple（苹果公司）
Generative adversarial networks (GANs), trained on a large-scale image dataset, can be a good approximator of the natural image manifold. GAN-inversion, using a pre-trained generator as a deep generative prior, is a promising tool for image restoration under corruptions. However, the performance of GAN-inversion can be limited by a lack of robustness to unknown gross corruptions, i.e., the restored image might easily deviate from the ground truth. In this paper, we propose a Robust GAN-inversion (RGI) method with a provable robustness guarantee to achieve image restoration under unknown \texti…
We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in videos into different objects. We introduce a novel pixel-trajectory recurrent neural network that learns feature embeddings of foreground pixel trajectories linked across time. By clustering the pixel trajectories using the learned feature embeddings, our method establishes correspondences between foreground object masks across video frames. To demonstrate the effectiveness of …
The task of unsupervised semantic segmentation aims to cluster pixels into semantically meaningful groups. Specifically, pixels assigned to the same cluster should share high-level semantic properties like their object or part category. This paper presents MaskDistill: a novel framework for unsupervised semantic segmentation based on three key ideas. First, we advocate a data-driven strategy to generate object masks that serve as a pixel grouping prior for semantic segmentation. This approach omits handcrafted priors, which are often designed for specific scene compositions and limit the appli…
China University of Geosciences（中国地质大学）；Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems（湖北省复杂系统先进控制与智能自动化重点实验室）
In this paper, a novel algorithm called a non-local adaptive mean filter (NAMF) for removing salt-and-pepper (SAP) noise from corrupted images is presented. We employ an efficient window detector with adaptive size to detect the noise, the noisy pixel will be replaced by the combination of its neighboring pixels, and finally we use a SAP noise based non-local mean filter to reconstruct the intensity values of noisy pixels. Extensive experimental results demonstrate that NAMF can obtain better performance in terms of quality for restoring images at all levels of SAP noise.
TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection
XJTLU（西交利物浦大学）；University of Liverpool（利物浦大学）；China University of Petroleum (East China)（中国石油大学（华东））；Nanjing University of Information Science and Technology（南京信息工程大学）
Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results over a small set of pixel-level mask annotations and a large set of box annotations. The basic idea is exploring detection models to simplify the pixel-level supervised learning task and thus reduce the required amount of mask annotations. Our architecture, named DASNet, consists of three modules: detection, attention, and segmentation. The detection module de…
Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Lab（鹏城实验室）；DAMO Academy at Alibaba Group（阿里巴巴达摩院）
For image inpainting, the convolutional neural networks (CNN) in previous methods often adopt standard convolutional operator, which treats valid pixels and holes indistinguishably. As a result, they are limited in handling irregular holes and tend to produce color-discrepant and blurry inpainting result. Partial convolution (PConv) copes with this issue by conducting masked convolution and feature re-normalization conditioned only on valid pixels, but the mask-updating is handcrafted and independent with image structural information. In this paper, we present an edge-guided learnable bidirect…
Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
East China Normal University（华东师范大学）；Xiamen University（厦门大学）；Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Tencent（腾讯）；University of Sheffield（谢菲尔德大学）；University at Buffalo（布法罗大学）
University of Glasgow（格拉斯哥大学）；University of Leeds（利兹大学）
In this study, we have tailored a pixel tracking method for temporal extrapolation of the ventricular segmentation masks in cardiac magnetic resonance images. The pixel tracking process starts from the end-diastolic frame of the heart cycle using the available manually segmented images to predict the end-systolic segmentation mask. The superpixels approach is used to divide the raw images into smaller cells and in each time frame, new labels are assigned to the image cells which leads to tracking the movement of the heart wall elements through different frames. The tracked masks at the end of …
Image denoising is one of the fundamental problems in image processing. In this paper, a novel approach to suppress noise from the image is conducted by applying the interquartile range (IQR) which is one of the statistical methods used to detect outlier effect from a dataset. A window of size kXk was implemented to support IQR filter. Each pixel outside the IQR range of the kXk window is treated as noisy pixel. The estimation of the noisy pixels was obtained by local averaging. The essential advantage of applying IQR filter is to preserve edge sharpness better of the original image. A variety…
The Hong Kong University of Science and Technology（香港科技大学）；SenseTime Research（商汤科技研究院）；University of Technology Sydney（悉尼科技大学）；The Hong Kong University of Science and Technology Shenzhen Research Institute（香港科技大学深圳研究院）
Weakly-Supervised Semantic Segmentation (WSSS) segments objects without a heavy burden of dense annotation. While as a price, generated pseudo-masks exist obvious noisy pixels, which result in sub-optimal segmentation models trained over these pseudo-masks. But rare studies notice or work on this problem, even these noisy pixels are inevitable after their improvements on pseudo-mask. So we try to improve WSSS in the aspect of noise mitigation. And we observe that many noisy pixels are of high confidence, especially when the response range is too wide or narrow, presenting an uncertain status. …
In remote sensing, image fusion technique is a useful tool used to fuse high spatial resolution panchromatic images (PAN) with lower spatial resolution multispectral images (MS) to create a high spatial resolution multispectral of image fusion (F) while preserving the spectral information in the multispectral image (MS).There are many PAN sharpening techniques or Pixel-Based image fusion techniques that have been developed to try to enhance the spatial resolution and the spectral property preservation of the MS. This paper attempts to undertake the study of image fusion, by using two types of …
Nanyang Technological University（南洋理工大学）；Kyushu University（九州大学）；Alibaba Group（阿里巴巴集团）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
Single-image deraining is rather challenging due to the unknown rain model. Existing methods often make specific assumptions of the rain model, which can hardly cover many diverse circumstances in the real world, making them have to employ complex optimization or progressive refinement. This, however, significantly affects these methods' efficiency and effectiveness for many efficiency-critical applications. To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i.e., EfficientDeRain, whic…
We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos. The mgPFF takes as input a pair of frames and outputs per-pixel filters to warp one frame to the other. Compared to optical flow used for warping frames, mgPFF is more powerful in modeling sub-pixel movement and dealing with corruption (e.g., motion blur). We develop a multigrid coarse-to-fine modeling strategy that avoids the requirement of learning large filters to capture large displacement. This allows us to train an extremely compact model (4.6MB) which operates in a progressive way ove…
Massachusetts Institute of Technology（麻省理工学院）；Skoltech（斯科尔科沃科学技术研究院）
In design of instance segmentation networks that reconstruct masks, segmentation is often taken as its literal definition -- assigning each pixel a label. This has led to thinking the problem as a template matching one with the goal of minimizing the loss between the reconstructed and the ground truth pixels. Rethinking reconstruction networks as a generator, we define the problem of predicting masks as a GANs game framework: A segmentation network generates the masks, and a discriminator network decides on the quality of the masks. To demonstrate this game, we show effective modifications on …
