State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided convolutions or successive dilated convolutions. However, it is not clear which operation leads to best results. In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN). FC-DRN has a densely connected backbone composed of residual networks. Following standard image segmentation architectures, receptive field enlargement operations that change the representation level are interleaved among residual networks. This allows the model to exploit the benefits of both residual and dense connectivity patterns, namely: gradient flow, iterative refinement of representations, multi-scale feature combination and deep supervision. In order to highlight the potential of our model, we test it on the challenging CamVid urban scene understanding benchmark and make the following observations: 1) downsampling operations outperform dilations when the model is trained from scratch, 2) dilations are useful during the finetuning step of the model, 3) coarser representations require less refinement steps, and 4) ResNets (by model construction) are good regularizers, since they can reduce the model capacity when needed. Finally, we compare our architecture to alternative methods and report state-of-the-art result on the Camvid dataset, with at least twice fewer parameters.
Institute of Automation, CAS（中国科学院自动化研究所）；School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院）；Youtu Lab, Tencent（腾讯优图实验室）；CASIA-LLVision Joint Lab（中国科学院自动化研究所-联汇视界联合实验室）；Y-Tech, Kuaishou Technology（快手科技Y-Tech）
Object detection has achieved remarkable progress in the past decade. However, the detection of oriented and densely packed objects remains challenging because of following inherent reasons: (1) receptive fields of neurons are all axis-aligned and of the same shape, whereas objects are usually of diverse shapes and align along various directions; (2) detection models are typically trained with generic knowledge and may not generalize well to handle specific objects at test time; (3) the limited dataset hinders the development on this task. To resolve the first two issues, we present a dynamic …
China University of Petroleum, Beijing Campus (CUP)（中国石油大学（北京））
The extensive research leveraging RGB-D information has been exploited in salient object detection. However, salient visual cues appear in various scales and resolutions of RGB images due to semantic gaps at different feature levels. Meanwhile, similar salient patterns are available in cross-modal depth images as well as multi-scale versions. Cross-modal fusion and multi-scale refinement are still an open problem in RGB-D salient object detection task. In this paper, we begin by introducing top-down and bottom-up iterative refinement architecture to leverage multi-scale features, and then devi…
Rutgers University（罗格斯大学）；Binghamton University（宾厄姆顿大学）；IBM T. J. Watson（IBM T. J. 沃森研究中心）；SenseTime（商汤科技）
In this paper, we propose quantized densely connected U-Nets for efficient visual landmark localization. The idea is that features of the same semantic meanings are globally reused across the stacked U-Nets. This dense connectivity largely improves the information flow, yielding improved localization accuracy. However, a vanilla dense design would suffer from critical efficiency issue in both training and testing. To solve this problem, we first propose order-K dense connectivity to trim off long-distance shortcuts; then, we use a memory-efficient implementation to significantly boost the trai…
iSeg: An Iterative Refinement-based Framework for Training-free Segmentation
School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；School of Big Data and Software Engineering, Chongqing University（重庆大学大数据与软件工程学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Linkoping University（林雪平大学）
Nanyang Technological University（南洋理工大学）；The University of Adelaide（阿德莱德大学）；China University of Mining and Technology（中国矿业大学）
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only make predictions within a set of pre-defined classes. In this paper, we present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Our network consists of a two-branch dense comparison module which performs multi-level feature comparison between the support image and the q…
Google DeepMind（谷歌DeepMind）；Applied AI Lab, University of Oxford（牛津大学应用人工智能实验室）
Advances in unsupervised learning of object-representations have culminated in the development of a broad range of methods for unsupervised object segmentation and interpretable object-centric scene generation. These methods, however, are limited to simulated and real-world datasets with limited visual complexity. Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations. In c…
VLM-Guided Iterative Refinement for Surgical Image Segmentation with Foundation Models
School of Automation Science and Engineering, South China University of Technology, Guangzhou, China（自动化科学与工程学院，华南理工大学，广州，中国）；Vanderbilt University, Nashville, TN, USA（范德比尔特大学，纳什维尔，田纳西州，美国）；The Pennsylvania State University, University Park, PA , USA（宾夕法尼亚州立大学，大学园，宾夕法尼亚州，美国）；Peking University, Beijing , China（北京大学，北京，中国）；Virginia Commonwealth University, Richmond, VA, USA（弗吉尼亚共同wealth大学，里士满，弗吉尼亚州，美国）；University of California San Diego, San Diego, CA, USA（加州大学圣地亚哥分校，圣地亚哥，加利福尼亚州，美国）
Image segmentation is often performed on medical images for identifying diseases in clinical evaluation. Hence it has become one of the major research areas. Conventional image segmentation techniques are unable to provide satisfactory segmentation results for medical images as they contain irregularities. They need to be pre-processed before segmentation. In order to obtain the most suitable method for medical image segmentation, we propose a two stage algorithm. The first stage automatically generates a binary marker image of the region of interest using mathematical morphology. This marker …
We address the task of 6D multi-object pose: given a set of known 3D objects and an RGB or RGB-D input image, we detect and estimate the 6D pose of each object. We propose a new approach to 6D object pose estimation which consists of an end-to-end differentiable architecture that makes use of geometric knowledge. Our approach iteratively refines both pose and correspondence in a tightly coupled manner, allowing us to dynamically remove outliers to improve accuracy. We use a novel differentiable layer to perform pose refinement by solving an optimization problem we refer to as Bidirectional Dep…
Australian National University（澳大利亚国立大学）；University of Technology（悉尼科技大学）
Object pose estimation from a single RGB image is a challenging problem due to variable lighting conditions and viewpoint changes. The most accurate pose estimation networks implement pose refinement via reprojection of a known, textured 3D model, however, such methods cannot be applied without high quality 3D models of the observed objects. In this work we propose an approach, namely an Innovation CNN, to object pose estimation refinement that overcomes the requirement for reprojecting a textured 3D model. Our approach improves initial pose estimation progressively by applying the Innovation …
Adobe Research（Adobe研究院）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））
Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos are untrimmed and only a video-level label is available. In this paper, we propose RefineLoc, a novel weakly-supervised temporal action localization method. RefineLoc uses an iterative refinement approach by estimating and training on snippet-level pseudo ground truth at every iteration. We show the benefit of this iterative approach and present an extensive…
We propose a new gradient-based method for the extraction of the orientation field associated to a fingerprint, and a regularisation procedure to improve the orientation field computed from noisy fingerprint images. The regularisation algorithm is based on three new integral operators, introduced and discussed in this paper. A pre-processing technique is also proposed to achieve better performances of the algorithm. The results of a numerical experiment are reported to give an evidence of the efficiency of the proposed algorithm.
Simon Fraser University（西蒙菲莎大学）；Autodesk Research（欧特克研究中心）
This paper proposes a novel generative adversarial layout refinement network for automated floorplan generation. Our architecture is an integration of a graph-constrained relational GAN and a conditional GAN, where a previously generated layout becomes the next input constraint, enabling iterative refinement. A surprising discovery of our research is that a simple non-iterative training process, dubbed component-wise GT-conditioning, is effective in learning such a generator. The iterative generator also creates a new opportunity in further improving a metric of choice via meta-optimization te…
Fraunhofer Institute for Telecommunications – Heinrich Hertz Institute（弗劳恩霍夫电信研究所——海因里希·赫兹研究所）；Technical University of Berlin（柏林工业大学）
This paper proposes an image interpolation algorithm exploiting sparse representation for natural images. It involves three main steps: (a) obtaining an initial estimate of the high resolution image using linear methods like FIR filtering, (b) promoting sparsity in a selected dictionary through iterative thresholding, and (c) extracting high frequency information from the approximation to refine the initial estimate. For the sparse modeling, a shearlet dictionary is chosen to yield a multiscale directional representation. The proposed algorithm is compared to several state-of-the-art methods t…
Seoul National University（首尔大学）；Qualcomm Technologies, Inc.（高通技术公司）
While hand pose estimation is a critical component of most interactive extended reality and gesture recognition systems, contemporary approaches are not optimized for computational and memory efficiency. In this paper, we propose a tiny deep neural network of which partial layers are recursively exploited for refining its previous estimations. During its iterative refinements, we employ learned gating criteria to decide whether to exit from the weight-sharing loop, allowing per-sample adaptation in our model. Our network is trained to be aware of the uncertainty in its current predictions to e…
Jagiellonian University（雅盖隆大学）；MILA（蒙特利尔学习算法研究所）；Université de Montréal（蒙特利尔大学）；Facebook（脸书）；Aalto University（阿尔托大学）；University of Bonn（波恩大学）
Residual networks (Resnets) have become a prominent architecture in deep learning. However, a comprehensive understanding of Resnets is still a topic of ongoing research. A recent view argues that Resnets perform iterative refinement of features. We attempt to further expose properties of this aspect. To this end, we study Resnets both analytically and empirically. We formalize the notion of iterative refinement in Resnets by showing that residual connections naturally encourage features of residual blocks to move along the negative gradient of loss as we go from one block to the next. In addi…
PLA Strategic Support Force Information Engineering University（中国人民解放军战略支援部队信息工程大学）；University of Trento（特伦托大学）
Deep learning based methods have seen a massive rise in popularity for hyperspectral image classification over the past few years. However, the success of deep learning is attributed greatly to numerous labeled samples. It is still very challenging to use only a few labeled samples to train deep learning models to reach a high classification accuracy. An active deep-learning framework trained by an end-to-end manner is, therefore, proposed by this paper in order to minimize the hyperspectral image classification costs. First, a deep densely connected convolutional network is considered for hyp…
Recently, the power of unconditional image synthesis has significantly advanced through the use of Generative Adversarial Networks (GANs). The task of inverting an image into its corresponding latent code of the trained GAN is of utmost importance as it allows for the manipulation of real images, leveraging the rich semantics learned by the network. Recognizing the limitations of current inversion approaches, in this work we present a novel inversion scheme that extends current encoder-based inversion methods by introducing an iterative refinement mechanism. Instead of directly predicting the …
Tsinghua University（清华大学）；BNRist（北京国家信息科学与技术研究中心）；University of Washington（华盛顿大学）
While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc. Orthogonal to them, this work presents a category-level object pose and size refiner CATRE, which is able to iteratively enhance pose estimate from point clouds to produce accurate results. Given an initial pose estimate, CATRE predicts a relative transformation between the initial pose and ground truth by means of aligning the partially observed point cloud and an …
IT-TextFusion: Iterative Text-Image Interaction with Text-Guided Residual Refinement for Degradation-Aware Image Fusion
School of Automation, Southeast University（东南大学自动化学院）；Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich（慕尼黑工业大学机器人、人工智能与实时系统研究所）
Single image surface normal estimation and depth estimation are closely related problems as the former can be calculated from the latter. However, the surface normals computed from the output of depth estimation methods are significantly less accurate than the surface normals directly estimated by networks. To reduce such discrepancy, we introduce a novel framework that uses surface normal and its uncertainty to recurrently refine the predicted depth-map. The depth of each pixel can be propagated to a query pixel, using the predicted surface normal as guidance. We thus formulate depth refineme…
In this work, a simple and efficient dual iterative refinement (DIR) method is proposed for dense correspondence between two nearly isometric shapes. The key idea is to use dual information, such as spatial and spectral, or local and global features, in a complementary and effective way, and extract more accurate information from current iteration to use for the next iteration. In each DIR iteration, starting from current correspondence, a zoom-in process at each point is used to select well matched anchor pairs by a local mapping distortion criterion. These selected anchor pairs are then used…
Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence（伯努利数学、计算机科学与人工智能研究所）；University of Groningen（格罗宁根大学）
This paper presents a novel iterative deep learning framework and apply it for document enhancement and binarization. Unlike the traditional methods which predict the binary label of each pixel on the input image, we train the neural network to learn the degradations in document images and produce the uniform images of the degraded input images, which allows the network to refine the output iteratively. Two different iterative methods have been studied in this paper: recurrent refinement (RR) which uses the same trained neural network in each iteration for document enhancement and stacked refi…
IMPROVE: Iterative Model Pipeline Refinement and Optimization Leveraging LLM Experts
University of Toronto（多伦多大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；New York University（纽约大学）
Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Deep learning approaches to optical flow estimation have seen rapid progress over the recent years. One common trait of many networks is that they refine an initial flow estimate either through multiple stages or across the levels of a coarse-to-fine representation. While leading to more accurate results, the downside of this is an increased number of parameters. Taking inspiration from both classical energy minimization approaches as well as residual networks, we propose an iterative residual refinement (IRR) scheme based on weight sharing that can be combined with several backbone networks. …
TU Wien（维也纳工业大学）；Automation and Control Institute（自动化与控制研究所）
Accurate and robust object pose estimation for robotics applications requires verification and refinement steps. In this work, we propose to integrate hypotheses verification with object pose refinement guided by physics simulation. This allows the physical plausibility of individual object pose estimates and the stability of the estimated scene to be considered in a unified optimization. The proposed method is able to adapt to scenes of multiple objects and efficiently focuses on refining the most promising object poses in multi-hypotheses scenarios. We call this integrated approach VeREFINE …
We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models to conditional image generation and performs super-resolution through a stochastic denoising process. Inference starts with pure Gaussian noise and iteratively refines the noisy output using a U-Net model trained on denoising at various noise levels. SR3 exhibits strong performance on super-resolution tasks at different magnification factors, on faces and natural images. We conduct human evaluation on a standard 8X face super-resolution task on CelebA-HQ, comparing…
University of California, Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）
Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This property enables the application of such methods to infer representations of sets of entities, such as objects in physical scenes, structurally resembling clustering algorithms in latent space. However, most prior works differentiate through the unrolled refinement process, which can make optimization challenging. We observe that such methods can be made diffe…
Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement
Department of Computer Science and Engineering, Dongguk University（计算机科学与工程系，东国大学）；Department of Computer Science and Artificial Intelligence, Dongguk University（计算机科学与人工智能系，东国大学）
The Image-Based Rendering (IBR) approach using Shearlet Transform (ST) is one of the most effective methods for Densely-Sampled Light Field (DSLF) reconstruction. The ST-based DSLF reconstruction typically relies on an iterative thresholding algorithm for Epipolar-Plane Image (EPI) sparse regularization in shearlet domain, involving dozens of transformations between image domain and shearlet domain, which are in general time-consuming. To overcome this limitation, a novel learning-based ST approach, referred to as Deep Residual Shearlet Transform (DRST), is proposed in this paper. Specifically…
MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline
Buzzni AI Lab（Buzzni人工智能实验室）；KAIST（韩国科学技术院）；Mathpresso Inc.（Mathpresso公司）；UC Berkeley（加州大学伯克利分校）；Fainders AI（Fainders人工智能公司）；Seoul National University（首尔大学）
Wide-angle cameras are uniquely positioned for mobile robots, by virtue of the rich information they provide in a small, light, and cost-effective form factor. An accurate calibration of the intrinsics and extrinsics is a critical pre-requisite for using the edge of a wide-angle lens for depth perception and odometry. Calibrating wide-angle lenses with current state-of-the-art techniques yields poor results due to extreme distortion at the edge, as most algorithms assume a lens with low to medium distortion closer to a pinhole projection. In this work we present our methodology for accurate wi…
The Pennsylvania State University（宾夕法尼亚州立大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
In this letter, we address sparse signal recovery using spike and slab priors. In particular, we focus on a Bayesian framework where sparsity is enforced on reconstruction coefficients via probabilistic priors. The optimization resulting from spike and slab prior maximization is known to be a hard non-convex problem, and existing solutions involve simplifying assumptions and/or relaxations. We propose an approach called Iterative Convex Refinement (ICR) that aims to solve the aforementioned optimization problem directly allowing for greater generality in the sparse structure. Essentially, ICR …
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）
Magnetic Resonance Imaging (MRI) has become an important technique in the clinic for the visualization, detection, and diagnosis of various diseases. However, one bottleneck limitation of MRI is the relatively slow data acquisition process. Fast MRI based on k-space undersampling and high-quality image reconstruction has been widely utilized, and many deep learning-based methods have been developed in recent years. Although promising results have been achieved, most existing methods require fully-sampled reference data for training the deep learning models. Unfortunately, fully-sampled MRI dat…
