Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning condition-aware embeddings. While such embeddings aid models in learning different notions of similarity, they also limit their capability to generalize to unseen categories since they require explicit labels at test time. To address this deficiency, we propose an approach that jointly learns representations for the different similarity conditions and their contributions as a latent variable without explicit supervision. Comprehensive experiments across three datasets, Polyvore-Outfits, Maryland-Polyvore and UT-Zappos50k, demonstrate the effectiveness of our approach: our model outperforms the state-of-the-art methods, even those that are strongly supervised with pre-defined similarity conditions, on fill-in-the-blank, outfit compatibility prediction and triplet prediction tasks. Finally, we show that our model learns different visually-relevant semantic sub-spaces that allow it to generalize well to unseen categories.
Ant Group（蚂蚁集团）；Copyright Protection Center of China（中国版权保护中心）
Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main …
University of Groningen（格罗宁根大学）；University of Twente（特文特大学）
Visual place recognition (VPR) is a fundamental task of computer vision for visual localization. Existing methods are trained using image pairs that either depict the same place or not. Such a binary indication does not consider continuous relations of similarity between images of the same place taken from different positions, determined by the continuous nature of camera pose. The binary similarity induces a noisy supervision signal into the training of VPR methods, which stall in local minima and require expensive hard mining algorithms to guarantee convergence. Motivated by the fact that tw…
Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convolutional network to exploit structure in scene graphs and produce image embeddings useful for semantic image retrieval. Different from classification-centric supervision traditionally available for learning image representations, we address the task of learning from relative similarity labels in a ranking context. Rooted within the contrastive learning paradigm, we propose a no…
Heidelberg Collaboratory for Image Processing（海德堡图像处理联合实验室）；Heidelberg University（海德堡大学）
Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs or triplets of samples. Many of these relations are unreliable and mutually contradicting, implying inconsistencies when trained without supervision information that relates different tuples or triplets to each other. To overcome this problem, we use local estimates of reliable (dis-)similarities to initially group samples into compact surrogate classes and…
We propose a novel method for learning convolutional neural image representations without manual supervision. We use motion cues in the form of optical flow, to supervise representations of static images. The obvious approach of training a network to predict flow from a single image can be needlessly difficult due to intrinsic ambiguities in this prediction task. We instead propose a much simpler learning goal: embed pixels such that the similarity between their embeddings matches that between their optical flow vectors. At test time, the learned deep network can be used without access to vide…
Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not. Such a binary indicator covers only a limited subset of image relations, and is not sufficient to represent semantic similarity between images described by continuous and/or structured labels such as object poses, image captions, and scene graphs. Motivated by this, we present a novel method for deep metric learning using continuous labels. First, we propose a new triplet loss that allows distance ratios in the label space to be preserved in the learned …
Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision
Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（谢仁明教授智能工程学院，华南理工大学）；School of Electrical and Computer Engineering, Georgia Institute of Technology（电气与计算机工程学院，佐治亚理工学院）；School of Electrical and Electronic Engineering, Nanyang Technological University（电子与电气工程学院，南洋理工大学）
University of Louisville（路易斯维尔大学）；Captricity, Inc.（Captricity公司）
In this paper, we propose a new text recognition model based on measuring the visual similarity of text and predicting the content of unlabeled texts. First a Siamese convolutional network is trained with deep supervision on a labeled training dataset. This network projects texts into a similarity manifold. The Deeply Supervised Siamese network learns visual similarity of texts. Then a K-nearest neighbor classifier is used to predict unlabeled text based on similarity distance to labeled texts. The performance of the model is evaluated on three datasets of machine-print and hand-written text c…
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background. Our method relies on moving objects being equivariant with respect to their transformation across frames and the background being constant. After training, we can manipulate and render the scenes in real time to create unseen combinations of objects, transformations, and backgrounds. We show results on moving MNIST with backgrounds.
The Johns Hopkins University（约翰斯·霍普金斯大学）；Johns Hopkins Medical Institutions（约翰斯·霍普金斯医学机构）；Laboratory for Computational Sensing and Robotics, The Johns Hopkins University（约翰斯·霍普金斯大学计算感知与机器人实验室）
In this work, we explore whether it is possible to learn representations of endoscopic video frames to perform tasks such as identifying surgical tool presence without supervision. We use a maximum mean discrepancy (MMD) variational autoencoder (VAE) to learn low-dimensional latent representations of endoscopic videos and manipulate these representations to distinguish frames containing tools from those without tools. We use three different methods to manipulate these latent representations in order to predict tool presence in each frame. Our fully unsupervised methods can identify whether end…
Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various challenging scenarios. The premier methods are those based on supervision requiring a final training stage on a database of tens to hundreds of manually segmented images from the specific static camera. In this work, we propose a method to automatically create an "artificial" database that is sufficient for training the supervised methods so that it performs better than current unsupervised methods. It is based on com…
Novel View Synthesis (NVS) is concerned with synthesizing views under camera viewpoint transformations from one or multiple input images. NVS requires explicit reasoning about 3D object structure and unseen parts of the scene to synthesize convincing results. As a result, current approaches typically rely on supervised training with either ground truth 3D models or multiple target images. We propose Continuous Object Representation Networks (CORN), a conditional architecture that encodes an input image's geometry and appearance that map to a 3D consistent scene representation. We can train COR…
A 3D scene consists of a set of objects, each with a shape and a layout giving their position in space. Understanding 3D scenes from 2D images is an important goal, with applications in robotics and graphics. While there have been recent advances in predicting 3D shape and layout from a single image, most approaches rely on 3D ground truth for training which is expensive to collect at scale. We overcome these limitations and propose a method that learns to predict 3D shape and layout for objects without any ground truth shape or layout information: instead we rely on multi-view images with 2D …
Imperial College London（帝国理工学院）；BioMedIA Group, Department of Computing（计算系BioMedIA小组）
Few-shot semantic segmentation (FSS) has great potential for medical imaging applications. Most of the existing FSS techniques require abundant annotated semantic classes for training. However, these methods may not be applicable for medical images due to the lack of annotations. To address this problem we make several contributions: (1) A novel self-supervised FSS framework for medical images in order to eliminate the requirement for annotations during training. Additionally, superpixel-based pseudo-labels are generated to provide supervision; (2) An adaptive local prototype pooling module pl…
Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typically addressed by matching local descriptors. Recently, a few attempts at applying the deep learning paradigm to the task have shown promising results. Yet, the only explored way to learn rotation invariant descriptors has been to feed neural networks with highly engineered and invariant representations provided by existing hand-crafted descriptors, a path that goes in the opposite direction of end-to-end learning from raw data so successfully deployed for 2D images. In this paper, we explore the b…
National and Kapodistrian University of Athens（雅典国立卡波迪斯特里安大学）；Athena RC（雅典娜研究中心）；Stanford University（斯坦福大学）；Institute of Advanced Research in Artificial Intelligence (IARAI)（人工智能高级研究所（IARAI））
Impressive progress in generative models and implicit representations gave rise to methods that can generate 3D shapes of high quality. However, being able to locally control and edit shapes is another essential property that can unlock several content creation applications. Local control can be achieved with part-aware models, but existing methods require 3D supervision and cannot produce textures. In this work, we devise PartNeRF, a novel part-aware generative model for editable 3D shape synthesis that does not require any explicit 3D supervision. Our model generates objects as a set of loca…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large training set of in-the-wild images, which by construction, lack ground truth 3D shape. To train a network without any 2D-to-3D supervision, we present RingNet, which learns to compute 3D face shape from a single image. Our key observation is that an individual's face shape is constant across images, regardless of expression, pose, lighting, etc. RingNet leverages multiple images of a person and automatically detect…
Much of recent research has been devoted to video prediction and generation, yet most of the previous works have demonstrated only limited success in generating videos on short-term horizons. The hierarchical video prediction method by Villegas et al. (2017) is an example of a state-of-the-art method for long-term video prediction, but their method is limited because it requires ground truth annotation of high-level structures (e.g., human joint landmarks) at training time. Our network encodes the input frame, predicts a high-level encoding into the future, and then a decoder with access to th…
University of Pennsylvania（宾夕法尼亚大学）；Stanford University（斯坦福大学）
We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple, effective, and robust geometric algorithm that can segment objects in 3D scenes without annotations or training on scenes. We achieve such unsupervised segmentation by exploiting single object shape priors. We make two novel steps in that direction. First, we introduce equivariant shape representations to this problem to eliminate the complexity induced by the variation in object configuration. Second, we propose a novel EM algorithm that can iteratively refine segmentation masks using the equivariant shape prior.…
Existing vision based supervised approaches to lateral vehicle control are capable of directly mapping RGB images to the appropriate steering commands. However, they are prone to suffering from inadequate robustness in real world scenarios due to a lack of failure cases in the training data. In this paper, a framework for training a more robust and scalable model for lateral vehicle control is proposed. The framework only requires an unlabeled sequence of RGB images. The trained model takes a point cloud as input and predicts the lateral offset to a subsequent frame from which the steering ang…
Learning Object Semantic Similarity with Self-Supervision
Frankfurt Institute for Advanced Studies（法兰克福高级研究所）；Xidian-FIAS international Joint Research Center（西安电子科技大学-法兰克福高级研究所国际联合研究中心）；Goethe University（歌德大学）；The Hessian Center for Artificial Intelligence（黑森人工智能中心）
Boston University（波士顿大学）；Google Research（谷歌研究院）；University of Toronto（多伦多大学）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and minimal latency overhead. The proposed model takes into account joint location uncertainty due to occlusion from multiple views, and requires only 2D keypoint data for training. Our method outperforms both classical bundle adjustment and weakly-supervised monocular 3D baselines on the well-established Human3.6M dataset, as well as the more challenging in-the-wild Ski-Pose PTZ dat…
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features. This motivates us to preserve both robust and non-robust features and separate them with disentangled representation learning. Our proposed Adversarial Asymmetric Training (AAT) algorithm can reliably disentangle robust and non-robust representations without additional supervision on robustness. Empirical results show our meth…
In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available. However, labels are often noisy, especially in remote sensing where manually curated public datasets are rare. We study the multi-modal cadaster map alignment problem for which available annotations are mis-aligned polygons, resulting in noisy supervision. We subsequently set up a multiple-rounds training scheme which corrects the ground truth annotations at each round to better train the model at the next round. We show that it is possible to reduc…
In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene. This information can be represented using feature points, which is a list of spatial locations in learned feature maps of an input image. Previous works show that feature points learned using unsupervised pre-training or human supervision can provide good features for control tasks. In this paper, we show that it is possible to learn efficient feature point representations end-to-end, without the need for unsupervised pre-training, decoders, or additional losses. Our pr…
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立理工学院）；Facebook AI Research（脸书人工智能研究院）
Learning to navigate in a realistic setting where an agent must rely solely on visual inputs is a challenging task, in part because the lack of position information makes it difficult to provide supervision during training. In this paper, we introduce a novel approach for learning to navigate from image inputs without external supervision or reward. Our approach consists of three stages: learning a good representation of first-person views, then learning to explore using memory, and finally learning to navigate by setting its own goals. The model is trained with intrinsic rewards only so that …
Shanghai Jiao Tong University（上海交通大学）；EPFL（洛桑联邦理工学院）；Shanghai General Hospital（上海市第一人民医院）
Projection map (PM) from optical coherence tomography (OCT) B-scan is an important tool to diagnose retinal diseases, which typically requires retinal layer segmentation. In this study, we present a novel end-to-end framework to predict PMs from B-scans. Instead of segmenting retinal layers explicitly, we represent them implicitly as predicted coordinates. By pixel interpolation on uniformly sampled coordinates between retinal layers, the corresponding PMs could be easily obtained with pooling. Notably, all the operators are differentiable; therefore, this Differentiable Projection Module (DPM…
In this paper, we explore how three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework, which is trained without the need of training data with point to point correspondences. By leveraging diverse information from sequential layers of a standard ResNet-based architecture, we are able to extract keypoints and descriptors that encode local information using generic techniques such as local activation norms, channel grouping and dropping, and self-distillation. Subsequently, global information for image retrieval is …
University College London（伦敦大学学院）；Adobe Research（Adobe研究院）
Vector graphics are widely used to represent fonts, logos, digital artworks, and graphic designs. But, while a vast body of work has focused on generative algorithms for raster images, only a handful of options exists for vector graphics. One can always rasterize the input graphic and resort to image-based generative approaches, but this negates the advantages of the vector representation. The current alternative is to use specialized models that require explicit supervision on the vector graphics representation at training time. This is not ideal because large-scale high quality vector-graphi…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（图宾根大学）；Amazon（亚马逊）；ETAS GmbH, Bosch Group（博世集团ETAS有限公司）
Learning-based 3D reconstruction methods have shown impressive results. However, most methods require 3D supervision which is often hard to obtain for real-world datasets. Recently, several works have proposed differentiable rendering techniques to train reconstruction models from RGB images. Unfortunately, these approaches are currently restricted to voxel- and mesh-based representations, suffering from discretization or low resolution. In this work, we propose a differentiable rendering formulation for implicit shape and texture representations. Implicit representations have recently gained …
USC Institute for Creative Technologies（南加州大学创意技术研究所）；University of Southern California（南加州大学）；Pinscreen
Recent advances in 3D deep learning have shown that it is possible to train highly effective deep models for 3D shape generation, directly from 2D images. This is particularly interesting since the availability of 3D models is still limited compared to the massive amount of accessible 2D images, which is invaluable for training. The representation of 3D surfaces itself is a key factor for the quality and resolution of the 3D output. While explicit representations, such as point clouds and voxels, can span a wide range of shape variations, their resolutions are often limited. Mesh-based represe…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；Adobe Research（Adobe研究院）；Google Brain（谷歌大脑）
Understanding the 3D world is a fundamental problem in computer vision. However, learning a good representation of 3D objects is still an open problem due to the high dimensionality of the data and many factors of variation involved. In this work, we investigate the task of single-view 3D object reconstruction from a learning agent's perspective. We formulate the learning process as an interaction between 3D and 2D representations and propose an encoder-decoder network with a novel projection loss defined by the perspective transformation. More importantly, the projection loss enables the unsu…
Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision
Graduate School of Arts and Sciences, The University of Tokyo（东京大学文学部与科学研究科）；Graduate School of Engineering Science, The University of Osaka（大阪大学工程科学研究科）
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Monash University（莫纳什大学）
For challenging machine learning problems such as zero-shot learning and fine-grained categorization, embedding learning is the machinery of choice because of its ability to learn generic notions of similarity, as opposed to class-specific concepts in standard classification models. Embedding learning aims at learning discriminative representations of data such that similar examples are pulled closer, while pushing away dissimilar ones. Despite their exemplary performances, supervised embedding learning approaches require huge number of annotations for training. This restricts their applicabil…
When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the model is hallucinating based on priors in the dataset and/or the language model. The most common way of relating image regions with words in caption models is through an attention mechanism over the regions that are used as input to predict the next word. The model must therefore learn to predict the attentional weights without knowing the word it should loc…
We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes even unavailable. However, the task is highly unconstrained and thus ill-posed. To address this problem, we propose to introduce an auxiliary domain which shares a common underlying-structure space with the target domain, and we make a partially shared latent space assumption. The k…
Facebook AI Research（脸书人工智能研究院）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立理工学院）
Convolutional neural networks trained without supervision come close to matching performance with supervised pre-training, but sometimes at the cost of an even higher number of parameters. Extracting subnetworks from these large unsupervised convnets with preserved performance is of particular interest to make them less computationally intensive. Typical pruning methods operate during training on a task while trying to maintain the performance of the pruned network on the same task. However, in self-supervised feature learning, the training objective is agnostic on the representation transfera…
