We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. Using web screenshots unlocks a treasure trove of visual and textual cues that are not present in using image-text pairs. In S4, we leverage the inherent tree-structured hierarchy of HTML elements and the spatial localization to carefully design 10 pre-training tasks with large scale annotated data. These tasks resemble downstream tasks across different domains and the annotations are cheap to obtain. We demonstrate that, compared to current screenshot pre-training objectives, our innovative pre-training method significantly enhances performance of image-to-text model in nine varied and popular downstream tasks - up to 76.1% improvements on Table Detection, and at least 1% on Widget Captioning.
HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing Supervision
Southern University of Science and Technology, Shenzhen, China（南方科技大学，深圳，中国）；College of William and Mary, Williamsburg, VA 23185, USA（威廉玛丽学院，威廉斯堡，VA 23185，美国）；Peng Cheng Laboratory, Shenzhen, China（鹏城实验室，深圳，中国）
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Innovation Institute（上海创新研究院）
Enhancing Monocular Height Estimation via Weak Supervision from Imperfect Labels
Chair of Data Science in Earth Observation, Technical University of Munich (TUM)（地球观测数据科学教授职位，慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；School of Engineering and Design, Technical University of Munich (TUM)（工程与设计学院，慕尼黑技术大学）
Recent Salient Object Detection (SOD) systems are mostly based on Convolutional Neural Networks (CNNs). Specifically, Deeply Supervised Saliency (DSS) system has shown it is very useful to add short connections to the network and supervising on the side output. In this work, we propose a new SOD system which aims at designing a more efficient and effective way to pass back global information. Richer and Deeper Supervision (RDS) is applied to better combine features from each side output without demanding much extra computational space. Meanwhile, the backbone network used for SOD is normally p…
Enhancing Cross-Dataset Performance of Distracted Driving Detection With Score Softmax Classifier And Dynamic Gaussian Smoothing Supervision
State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body（汽车车身先进设计与制造国家重点实验室）；College of Mechanical and Vehicle Engineering, Hunan University（湖南大学机械与运载工程学院）；Faculty of Engineering and IT, University of Technology Sydney（悉尼科技大学工程与信息技术学院）；College of Automotive and Mechanical Engineering, ChangSha University of Science Technology（长沙理工大学汽车与机械工程学院）
Enhancing Visual Continual Learning with Language-Guided Supervision
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Centre for Artificial Intelligence and Robotics, HK Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）
Our brains combine vision and hearing to create a more elaborate interpretation of the world. When the visual input is insufficient, a rich panoply of sounds can be used to describe our surroundings. Since more than 1,000 hours of videos are uploaded to the internet everyday, it is arduous, if not impossible, to manually annotate these videos. Therefore, incorporating audio along with visual data without annotations is crucial for leveraging this explosion of data for recognizing and understanding objects and scenes. Owens,et.al suggest that a rich representation of the physical world can be l…
In this work we propose a technique that transfers supervision between images from different modalities. We use learned representations from a large labeled modality as a supervisory signal for training representations for a new unlabeled paired modality. Our method enables learning of rich representations for unlabeled modalities and can be used as a pre-training procedure for new modalities with limited labeled data. We show experimental results where we transfer supervision from labeled RGB images to unlabeled depth and optical flow images and demonstrate large improvements for both these c…
Semi-supervised semantic segmentation needs rich and robust supervision on unlabeled data. Consistency learning enforces the same pixel to have similar features in different augmented views, which is a robust signal but neglects relationships with other pixels. In comparison, contrastive learning considers rich pairwise relationships, but it can be a conundrum to assign binary positive-negative supervision signals for pixel pairs. In this paper, we take the best of both worlds and propose multi-view correlation consistency (MVCC) learning: it considers rich pairwise relationships in self-corre…
Monash University（莫纳什大学）；University of Adelaide（阿德莱德大学）
Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they only rely on the model's prediction to make labeling decisions without considering any prior knowledge about the visual similarity among the classes. In this paper, we demonstrate that this degrades the quality of pseudo-labeling as it poorly represents visually similar classes in the pool of pseudo-labeled data. We propose SemCo, a method which leverages lab…
Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To overcome these challenges, we propose a novel framework, namely Explicit Pseudo-pixel Supervision (EPS), which learns from pixel-level feedback by combining two weak supervisions; the image-level label provides the object identity via the localization map and the saliency map from the off-the-shelf saliency detection model offers rich boundaries. We devise a joint…
Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced. Many approaches to few-shot learning build on transferring a representation from well-sampled classes, or using meta learning to favor architectures that can learn with few samples. Unfortunately, such approaches often struggle when learning in an online way or with non-stationary data streams. Here we describe a new approach to learn with fewer samples, by…
In this paper we show how to perform scene-level inverse rendering to recover shape, reflectance and lighting from a single, uncontrolled image using a fully convolutional neural network. The network takes an RGB image as input, regresses albedo, shadow and normal maps from which we infer least squares optimal spherical harmonic lighting coefficients. Our network is trained using large uncontrolled multiview and timelapse image collections without ground truth. By incorporating a differentiable renderer, our network can learn from self-supervision. Since the problem is ill-posed we introduce a…
University of Oxford（牛津大学）；Xerox Research Centre Europe（施乐欧洲研究中心）
While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important. Recognizing object parts and attributes has been extensively studied before, yet learning large space of such concepts remains elusive due to the high cost of providing detailed object annotations for supervision. The key contribution of this paper is an algorithm to learn the nameable parts of objects automatically, from images obtained by querying Web search engines. The key challenge is the high level of noise in the annotations; to …
We show how to train a fully convolutional neural network to perform inverse rendering from a single, uncontrolled image. The network takes an RGB image as input, regresses albedo and normal maps from which we compute lighting coefficients. Our network is trained using large uncontrolled image collections without ground truth. By incorporating a differentiable renderer, our network can learn from self-supervision. Since the problem is ill-posed we introduce additional supervision: 1. We learn a statistical natural illumination prior, 2. Our key insight is to perform offline multiview stereo (M…
We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from freely available unlabeled web search results. The explosion of visual data on the web can potentially make visual examples of almost any object easily accessible via web search. Previous unsupervised methods have utilized either large scale sources of texture cues from the web, or shape information from data such as crowdsourced CAD models. We propose a two-stream deep learning framework that combines these cues, with o…
The Hong Kong University of Science and Technology（香港科技大学）；Nanyang Technological University（南洋理工大学）；The Hong Kong University of Science and Technology Shenzhen Research Institute（香港科技大学深圳研究院）
Self-supervised learning has witnessed great progress in vision and NLP; recently, it also attracted much attention to various medical imaging modalities such as X-ray, CT, and MRI. Existing methods mostly focus on building new pretext self-supervision tasks such as reconstruction, orientation, and masking identification according to the properties of medical images. However, the publicly available self-supervision models are not fully exploited. In this paper, we present a powerful yet efficient self-supervision framework for surgical video understanding. Our key insight is to distill knowled…
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learning focuses instead on unlabeled data and looks into it for the supervisory signal to feed high capacity deep neural networks. In this work we exploit the complementarity of these two domains and propose an approach for improving few-shot learning through self-supervision. We use self-supervision as …
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；The Hong Kong University of Science and Technology Shenzhen Research Institute（香港科技大学深圳研究院）
Generalizing the medical image segmentation algorithms to unseen domains is an important research topic for computer-aided diagnosis and surgery. Most existing methods require a fully labeled dataset in each source domain. Although some researchers developed a semi-supervised domain generalized method, it still requires the domain labels. This paper presents a novel confidence-aware cross pseudo supervision algorithm for semi-supervised domain generalized medical image segmentation. The main goal is to enhance the pseudo label quality for unlabeled images from unknown distributions. To achieve…
DS$^2$Net: Detail-Semantic Deep Supervision Network for Medical Image Segmentation
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China（教育部多媒体可信感知与高效计算重点实验室）；Xiamen University（厦门大学）；Computer Engineering College（计算机工程学院）
Recent studies on learning-based image denoising have achieved promising performance on various noise reduction tasks. Most of these deep denoisers are trained either under the supervision of clean references, or unsupervised on synthetic noise. The assumption with the synthetic noise leads to poor generalization when facing real photographs. To address this issue, we propose a novel deep image-denoising method by regarding the noise reduction task as a special case of the noise transference task. Learning noise transference enables the network to acquire the denoising ability by observing the…
PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳分校）；Meituan, Beijing（美团，北京）
Training object detection models usually requires instance-level annotations, such as the positions and labels of all objects present in each image. Such supervision is unfortunately not always available and, more often, only image-level information is provided, also known as weak supervision. Recent works have addressed this limitation by leveraging knowledge from a richly annotated domain. However, the scope of weak supervision supported by these approaches has been very restrictive, preventing them to use all available information. In this work, we propose ProbKT, a framework based on proba…
Microsoft Ads（微软广告）；Microsoft AI & Research（微软人工智能与研究院）
Contextual bandits are a common problem faced by machine learning practitioners in domains as diverse as hypothesis testing to product recommendations. There have been a lot of approaches in exploiting rich data representations for contextual bandit problems with varying degree of success. Self-supervised learning is a promising approach to find rich data representations without explicit labels. In a typical self-supervised learning scheme, the primary task is defined by the problem objective (e.g. clustering, classification, embedding generation etc.) and the secondary task is defined by the …
