The problem of computing category agnostic bounding box proposals is utilized as a core component in many computer vision tasks and thus has lately attracted a lot of attention. In this work we propose a new approach to tackle this problem that is based on an active strategy for generating box proposals that starts from a set of seed boxes, which are uniformly distributed on the image, and then progressively moves its attention on the promising image areas where it is more likely to discover well localized bounding box proposals. We call our approach AttractioNet and a core component of it is a CNN-based category agnostic object location refinement module that is capable of yielding accurate and robust bounding box predictions regardless of the object category.
We extensively evaluate our AttractioNet approach on several image datasets (i.e. COCO, PASCAL, ImageNet detection and NYU-Depth V2 datasets) reporting on all of them state-of-the-art results that surpass the previous work in the field by a significant margin and also providing strong empirical evidence that our approach is capable to generalize to unseen categories. Furthermore, we evaluate our AttractioNet proposals in the context of the object detection task using a VGG16-Net based detector and the achieved detection performance on COCO manages to significantly surpass all other VGG16-Net based detectors while even being competitive with a heavily tuned ResNet-101 based detector. Code as well as box proposals computed for several datasets are available at:: https://github.com/gidariss/AttractioNet.
In a dynamic environment, an agent with a limited field of view/resource cannot fully observe the scene before attempting to parse it. The deployment of common semantic segmentation architectures is not feasible in such settings. In this paper we propose a method to gradually segment a scene given a sequence of partial observations. The main idea is to refine an agent's understanding of the environment by attending the areas it is most uncertain about. Our method includes a self-supervised attention mechanism and a specialized architecture to maintain and exploit spatial memory maps for fillin…
Few-shot object detection aims to detect instances of specific categories in a query image with only a handful of support samples. Although this takes less effort than obtaining enough annotated images for supervised object detection, it results in a far inferior performance compared to the conventional object detection methods. In this paper, we propose a meta-learning-based approach that considers the unique characteristics of each support sample. Rather than simply averaging the information of the support samples to generate a single prototype per category, our method can better utilize the…
In this work we present Discrete Attend Infer Repeat (Discrete-AIR), a Recurrent Auto-Encoder with structured latent distributions containing discrete categorical distributions, continuous attribute distributions, and factorised spatial attention. While inspired by the original AIR model andretaining AIR model's capability in identifying objects in an image, Discrete-AIR provides direct interpretability of the latent codes. We show that for Multi-MNIST and a multiple-objects version of dSprites dataset, the Discrete-AIR model needs just one categorical latent variable, one attribute variable (…
We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep generative model for videos of moving objects. It can reliably discover and track objects throughout the sequence of frames, and can also generate future frames conditioning on the current frame, thereby simulating expected motion of objects. This is achieved by explicitly encoding object presence, locations and appearances in the latent variables of the model. SQAIR retains all strengths of its predecessor, Attend, Infer, Repeat (AIR, Eslami et. al., 2016), including learning in an unsupervised manner, and addresses it…
We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use this scheme to learn to perform inference in partially specified 2D models (variable-sized variational auto-encoders) and fully specified 3D models (probabilistic renderers). We show that such models learn to identify multiple objects - coun…
Attend-and-Refine: Interactive keypoint estimation and quantitative cervical vertebrae analysis for bone age assessment
Kim Jaechul Graduate School of Artificial Intelligence, KAIST, Daejeon 34141, Republic of Korea（韩国科学技术院人工智能研究生院）；Korea University Anam Hospital, Seoul 02708, Republic of Korea（韩国大学安安医院）；Asan Medical Center, University of Ulsan College of Medicine, Seoul 05505, Republic of Korea（釜山大学医学院_asan医院）
Anhui University（安徽大学）；University of Chinese Academy of Sciences（中国科学院大学）
The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples independently while ignores the relationship information among them. In this paper, we propose a novel structure-aware deep neural network to overcome such limitations. In particular, we construct a graph to represent the pairwise relationships among training samples, and additionally take the natural language as the supervised information to learn both feature re…
The task of estimating the 6D pose of an object from RGB images can be broken down into two main steps: an initial pose estimation step, followed by a refinement procedure to correctly register the object and its observation. In this paper, we propose a new method for 6D pose estimation refinement from RGB images. To achieve high accuracy of the final estimate, the observation and a rendered model need to be aligned. Our main insight is that after the initial pose estimate, it is important to pay attention to distinct spatial features of the object in order to improve the estimation accuracy d…
Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features and propagate large errors to the final geometry. In this paper, we refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views: we first adjust the initial keypoint locations prior to any geometric estimation, and subsequently refine points and camera poses as a post-processing. This refinement is robu…
Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and are difficult to generalize to unseen classes. Few-shot learning has the potential to address these challenges by learning new classes from only a few labeled examples. In this work, we propose a new framework for few-shot medical image segmentation based on prototypical networks. Our innovation lies in the design of two key modules: 1) a context relation encoder (CRE) that uses correlation to capture local relation fe…
Facial landmark localization plays an important role in face recognition and analysis applications. In this paper, we give a brief introduction to a coarse-to-fine pipeline with neural networks and sequential regression. First, a global convolutional network is applied to the holistic facial image to give an initial landmark prediction. A pyramid of multi-scale local image patches is then cropped to feed to a new network for each landmark to refine the prediction. As the refinement network outputs a more accurate position estimation than the input, such procedure could be repeated several time…
Google Inc.（谷歌公司）；Georgia Institute of Technology（佐治亚理工学院）
We present a technique that uses images, videos and sensor data taken from first-person point-of-view devices to perform egocentric field-of-view (FOV) localization. We define egocentric FOV localization as capturing the visual information from a person's field-of-view in a given environment and transferring this information onto a reference corpus of images and videos of the same space, hence determining what a person is attending to. Our method matches images and video taken from the first-person perspective with the reference corpus and refines the results using the first-person's head orie…
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 Maryland Institute for Advanced Computer Studies（马里兰大学高级计算机研究所）；University of Maryland（马里兰大学）
Recent advances in object segmentation have demonstrated that deep neural networks excel at object segmentation for specific classes in color and depth images. However, their performance is dictated by the number of classes and objects used for training, thereby hindering generalization to never seen objects or zero-shot samples. To exacerbate the problem further, object segmentation using image frames rely on recognition and pattern matching cues. Instead, we utilize the 'active' nature of a robot and their ability to 'interact' with the environment to induce additional geometric constraints …
Zhejiang University（浙江大学）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
Grounded video description (GVD) encourages captioning models to attend to appropriate video regions (e.g., objects) dynamically and generate a description. Such a setting can help explain the decisions of captioning models and prevents the model from hallucinating object words in its description. However, such design mainly focuses on object word generation and thus may ignore fine-grained information and suffer from missing visual concepts. Moreover, relational words (e.g., "jump left or right") are usual spatio-temporal inference results, i.e., these words cannot be grounded on certain spat…
