Dramatic demand for manpower to label pixel-level annotations triggered the advent of unsupervised semantic segmentation. Although the recent work employing the vision transformer (ViT) backbone shows exceptional performance, there is still a lack of consideration for task-specific training guidance and local semantic consistency. To tackle these issues, we leverage contrastive learning by excavating hidden positives to learn rich semantic relationships and ensure semantic consistency in local regions. Specifically, we first discover two types of global hidden positives, task-agnostic and task-specific ones for each anchor based on the feature similarities defined by a fixed pre-trained backbone and a segmentation head-in-training, respectively. A gradual increase in the contribution of the latter induces the model to capture task-specific semantic features. In addition, we introduce a gradient propagation strategy to learn semantic consistency between adjacent patches, under the inherent premise that nearby patches are highly likely to possess the same semantics. Specifically, we add the loss propagating to local hidden positives, semantically similar nearby patches, in proportion to the predefined similarity scores. With these training schemes, our proposed method achieves new state-of-the-art (SOTA) results in COCO-stuff, Cityscapes, and Potsdam-3 datasets. Our code is available at: https://github.com/hynnsk/HP.
University of Oxford（牛津大学）；University of Cambridge（剑桥大学）；Shanghai Jiao Tong University（上海交通大学）
In this paper, we tackle the challenging task of unsupervised salient object detection (SOD) by leveraging spectral clustering on self-supervised features. We make the following contributions: (i) We revisit spectral clustering and demonstrate its potential to group the pixels of salient objects; (ii) Given mask proposals from multiple applications of spectral clustering on image features computed from various self-supervised models, e.g., MoCov2, SwAV, DINO, we propose a simple but effective winner-takes-all voting mechanism for selecting the salient masks, leveraging object priors based on f…
Simon Fraser University（西蒙弗雷泽大学）；Microsoft Research（微软研究院）
We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos online, which exhibit large illumination variations that make them suitable for training of reflectance separation and can facilitate object-level decomposition. The main contribution of our approach is a proposed image representation based on local color distributions that allows training to be insensitive to the local misalignments of multi-view images. In…
Person re-identification (re-ID) is a challenging problem especially when no labels are available for training. Although recent deep re-ID methods have achieved great improvement, it is still difficult to optimize deep re-ID model without annotations in training data. To address this problem, this study introduces a novel approach for unsupervised person re-ID by leveraging virtual and real data. Our approach includes two components: virtual person generation and training of deep re-ID model. For virtual person generation, we learn a person generation model and a camera style transfer model us…
FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；College of Mechatronics and Control Engineering, Shenzhen University（深圳大学机电与控制工程学院）
University Paris-Est Créteil (UPEC)（巴黎东克雷泰伊大学）；University Sud Toulon-Var（南土伦瓦尔大学）；University Paris-Est（巴黎东大学）；IFSTTAR（法国交通发展与网络科学研究院）
Using supervised machine learning approaches to recognize human activities from on-body wearable accelerometers generally requires a large amount of labelled data. When ground truth information is not available, too expensive, time consuming or difficult to collect, one has to rely on unsupervised approaches. This paper presents a new unsupervised approach for human activity recognition from raw acceleration data measured using inertial wearable sensors. The proposed method is based upon joint segmentation of multidimensional time series using a Hidden Markov Model (HMM) in a multiple regressi…
Wuhan University（武汉大学）；Finnish Geospatial Research Institute（芬兰地理空间研究所）；Hubei University of Technology（湖北工业大学）
As an important technology in 3D mapping, autonomous driving, and robot navigation, LiDAR odometry is still a challenging task. Appropriate data structure and unsupervised deep learning are the keys to achieve an easy adjusted LiDAR odometry solution with high performance. Utilizing compact 2D structured spherical ring projection model and voxel model which preserves the original shape of input data, we propose a fully unsupervised Convolutional Auto-Encoder based LiDAR Odometry (CAE-LO) that detects interest points from spherical ring data using 2D CAE and extracts features from multi-resolut…
The Hamlyn Centre for Robotic Surgery, Imperial College London（伦敦帝国理工学院哈姆林机器人手术中心）；The Kennedy Institute of Rheumatology, University of Oxford（牛津大学肯尼迪风湿病学研究所）
Depth estimation from a stereo image pair has become one of the most explored applications in computer vision, with most of the previous methods relying on fully supervised learning settings. However, due to the difficulty in acquiring accurate and scalable ground truth data, the training of fully supervised methods is challenging. As an alternative, self-supervised methods are becoming more popular to mitigate this challenge. In this paper, we introduce the H-Net, a deep-learning framework for unsupervised stereo depth estimation that leverages epipolar geometry to refine stereo matching. For…
Institute for Applied Computational Science, Harvard University（哈佛大学应用计算科学研究所）；Google Brain（谷歌大脑）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Learning to predict scene depth from RGB inputs is a challenging task both for indoor and outdoor robot navigation. In this work we address unsupervised learning of scene depth and robot ego-motion where supervision is provided by monocular videos, as cameras are the cheapest, least restrictive and most ubiquitous sensor for robotics. Previous work in unsupervised image-to-depth learning has established strong baselines in the domain. We propose a novel approach which produces higher quality results, is able to model moving objects and is shown to transfer across data domains, e.g. from outdoo…
This work considers the problem of learning structured representations from raw images using self-supervised learning. We propose a principled framework based on a mutual information objective, which integrates self-supervised and structure learning. Furthermore, we devise a post-hoc procedure to interpret the meaning of the learnt representations. Preliminary experiments on CIFAR-10 show that the proposed framework achieves higher generalization performance in downstream classification tasks and provides more interpretable representations compared to the ones learnt through traditional self-s…
Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization
LIVIA；ÉTS；ILLS；McGill（麦吉尔大学）；Mila；CNRS（法国国家科学研究中心）；Université Paris-Saclay（巴黎萨克雷大学）；CentraleSupelec（中央理工学院）；CHU Sainte-Justine（圣贾斯汀大学医疗中心）；University of Montreal（蒙特利尔大学）；Murdoch Children’s Research Institute（默多克儿童研究所）；Monash University（莫纳什大学）；The University of Melbourne（墨尔本大学）；The Royal Women’s Hospital（皇家妇女医院）
Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）
We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, we employ a two step strategy that a) does unsupervised discovery, via generative models, of sensitive factors that cause models to under-perform, and b) intervenes models to make their performance invariant to these sensitive factors' influence. We consider 3 separate interventions for robustness, including: data augmentation, semantic consistency, and adversarial alignment. We e…
MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；Institute for Advanced Study（高等研究院）；Princeton Neuroscience Institute（普林斯顿神经科学研究所）；Princeton University（普林斯顿大学）
It is widely believed that the backpropagation algorithm is essential for learning good feature detectors in early layers of artificial neural networks, so that these detectors are useful for the task performed by the higher layers of that neural network. At the same time, the traditional form of backpropagation is biologically implausible. In the present paper we propose an unusual learning rule, which has a degree of biological plausibility, and which is motivated by Hebb's idea that change of the synapse strength should be local - i.e. should depend only on the activities of the pre and pos…
When Unsupervised Domain Adaptation meets One-class Anomaly Detection: Addressing the Two-fold Unsupervised Curse by Leveraging Anomaly Scarcity
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（安全、可靠性与信任跨学科研究中心（SnT），卢森堡大学）；Cristal Laboratory, National School of Computer Sciences, University of Manouba（晶体实验室，国家计算机科学学校，曼努巴大学）
Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
University of Campinas（坎皮纳斯大学）；Institute of Computing, University of Campinas（坎皮纳斯大学计算学院）；Center for Information Technology Renato Archer (CTI)（雷纳托·阿彻信息技术中心（CTI））
Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion
City University of Hong Kong（香港城市大学）；Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）生物计算研究中心）；Shenzhen Key Laboratory of Visual Object Detection and Recognition（深圳市视觉目标检测与识别重点实验室）
Information Technology University（信息技术大学）；University of Toronto（多伦多大学）
Among the plethora of techniques devised to curb the prevalence of noise in medical images, deep learning based approaches have shown the most promise. However, one critical limitation of these deep learning based denoisers is the requirement of high-quality noiseless ground truth images that are difficult to obtain in many medical imaging applications such as X-rays. To circumvent this issue, we leverage recently proposed approach of [7] that incorporates Stein's Unbiased Risk Estimator (SURE) to train a deep convolutional neural network without requiring denoised ground truth X-ray data. Our…
Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking
Information Systems Technology and Design Pillar, Singapore University of Technology and Design（新加坡科技设计大学信息系统技术与设计学院）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；Department of Computer Science and Engineering, University at Buffalo, State University of New York（纽约州立大学布法罗分校计算机科学与工程系）；School of Computer Science, Wuhan University（武汉大学计算机学院）
Automatic segmentation of brain abnormalities is challenging, as they vary considerably from one pathology to another. Current methods are supervised and require numerous annotated images for each pathology, a strenuous task. To tackle anatomical variability, Unsupervised Anomaly Detection (UAD) methods are proposed, detecting anomalies as outliers of a healthy model learned using a Variational Autoencoder (VAE). Previous work on UAD adopted a 2D approach, meaning that MRIs are processed as a collection of independent slices. Yet, it does not fully exploit the spatial information contained in …
Although 3D point cloud classification neural network models have been widely used, the in-depth interpretation of the activation of the neurons and layers is still a challenge. We propose a novel approach, named Relevance Flow, to interpret the hidden semantics of 3D point cloud classification neural networks. It delivers the class Relevance to the activated neurons in the intermediate layers in a back-propagation manner, and associates the activation of neurons with the input points to visualize the hidden semantics of each layer. Specially, we reveal that the 3D point cloud classification n…
EDF R&D（法国电力集团研发中心）；CEDRIC, Conservatoire National des Arts et Métiers（法国国立工艺学院CEDRIC实验室）
Leveraging physical knowledge described by partial differential equations (PDEs) is an appealing way to improve unsupervised video prediction methods. Since physics is too restrictive for describing the full visual content of generic videos, we introduce PhyDNet, a two-branch deep architecture, which explicitly disentangles PDE dynamics from unknown complementary information. A second contribution is to propose a new recurrent physical cell (PhyCell), inspired from data assimilation techniques, for performing PDE-constrained prediction in latent space. Extensive experiments conducted on four v…
Supervision for image-to-image translation (I2I) tasks is hard to come by, but bears significant effect on the resulting quality. In this paper, we observe that for many Unsupervised I2I (UI2I) scenarios, one domain is more familiar than the other, and offers in-domain prior knowledge, such as semantic segmentation. We argue that for complex scenes, figuring out the semantic structure of the domain is hard, especially with no supervision, but is an important part of a successful I2I operation. We hence introduce two techniques to incorporate this invaluable in-domain prior knowledge for the be…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Feature-based visual simultaneous localization and mapping (SLAM) methods only estimate the depth of extracted features, generating a sparse depth map. To solve this sparsity problem, depth completion tasks that estimate a dense depth from a sparse depth have gained significant importance in robotic applications like exploration. Existing methodologies that use sparse depth from visual SLAM mainly employ point features. However, point features have limitations in preserving structural regularities owing to texture-less environments and sparsity problems. To deal with these issues, we perform d…
BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation
Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（巴黎-罗克琴court研究所）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）；University of North Carolina at Charlotte（北卡罗来纳大学教堂山分校）；Utah State University（犹他州立大学）
In current biological and medical research, statistical shape modeling (SSM) provides an essential framework for the characterization of anatomy/morphology. Such analysis is often driven by the identification of a relatively small number of geometrically consistent features found across the samples of a population. These features can subsequently provide information about the population shape variation. Dense correspondence models can provide ease of computation and yield an interpretable low-dimensional shape descriptor when followed by dimensionality reduction. However, automatic methods for…
State of the art Deep Neural Networks (DNN) can now achieve above human level accuracy on image classification tasks. However their outstanding performances come along with a complex inference mechanism making them arduously interpretable models. In order to understand the underlying prediction rules of DNNs, Dhamdhere et al. propose an interpretability method to break down a DNN prediction score as sum of its hidden unit contributions, in the form of a metric called conductance. Analyzing conductances of DNN hidden units, we find out there is a difference in how wrong and correct predictions …
We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. In this work, instead of simply generating pseudo-ground-truth sentences of training images using existing image captioning methods, we employ a pretrained CLIP model, which is capable of properly aligning embeddings of images and corresponding texts in a joint space and, consequently, works well on zero-shot recognition tasks. We optimize a text-to-image generation model by maximizing the data log-likelihood conditioned on pairs of image-text CLIP embedd…
