The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS). High-order features are usually developed to uncover subtle differences between sub-categories in FGFS, but they are less effective in handling the high intra-class variance. In this paper, we propose a Target-Oriented Alignment Network (TOAN) to investigate the fine-grained relation between the target query image and support classes. The feature of each support image is transformed to match the query ones in the embedding feature space, which reduces the disparity explicitly within each category. Moreover, different from existing FGFS approaches devise the high-order features over the global image with less explicit consideration of discriminative parts, we generate discriminative fine-grained features by integrating compositional concept representations to global second-order pooling. Extensive experiments are conducted on four fine-grained benchmarks to demonstrate the effectiveness of TOAN compared with the state-of-the-art models.
University of Technology, Sydney（悉尼科技大学）；Shanghai Jiao Tong University（上海交通大学）
In the context of fine-grained visual categorization, the ability to interpret models as human-understandable visual manuals is sometimes as important as achieving high classification accuracy. In this paper, we propose a novel Part-Stacked CNN architecture that explicitly explains the fine-grained recognition process by modeling subtle differences from object parts. Based on manually-labeled strong part annotations, the proposed architecture consists of a fully convolutional network to locate multiple object parts and a two-stream classification network that en- codes object-level and part-le…
Novel Class Discovery for Ultra-Fine-Grained Visual Categorization
International School of Information Science and Engineering, Dalian University of Technology（大连理工大学信息与工程国际学院）；Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）
Google Research（谷歌研究院）；Makerere University（马凯雷雷大学）；National Crops Resources Research Institute（国家作物资源研究所）
Viral diseases are major sources of poor yields for cassava, the 2nd largest provider of carbohydrates in Africa.At least 80% of small-holder farmer households in Sub-Saharan Africa grow cassava. Since many of these farmers have smart phones, they can easily obtain photos of dis-eased and healthy cassava leaves in their farms, allowing the opportunity to use computer vision techniques to monitor the disease type and severity and increase yields. How-ever, annotating these images is extremely difficult as ex-perts who are able to distinguish between highly similar dis-eases need to be employed.…
University of Technology Sydney（悉尼科技大学）；University of Electronic Science and Technology of China（电子科技大学）；Alibaba Group（阿里巴巴集团）；SouthEast University（东南大学）；Nanjing University of Science and Technology（南京理工大学）
Studies show that refining real-world categories into semantic subcategories contributes to better image modeling and classification. Previous image sub-categorization work relying on labeled images and WordNet's hierarchy is not only labor-intensive, but also restricted to classify images into NOUN subcategories. To tackle these problems, in this work, we exploit general corpus information to automatically select and subsequently classify web images into semantic rich (sub-)categories. The following two major challenges are well studied: 1) noise in the labels of subcategories derived from th…
Renmin University of China（中国人民大学）；Vistel AI Lab, Visionary Intelligence Ltd.（Vistel AI实验室，睿视智联科技有限公司）
Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA). Given labeled data from a source domain and unlabeled data from a target domain, UDA seeks for a deep representation that is both discriminative and domain-invariant. While UDA focuses on the target domain, we argue that the performance on both source and target domains matters, as in practice which domain a test example comes from is unknown. In this paper we e…
Peking University（北京大学）；China North Vehicle Research Institute（中国北方车辆研究所）
Categorizing driving scenes via visual perception is a key technology for safe driving and the downstream tasks of autonomous vehicles. Traditional methods infer scene category by detecting scene-related objects or using a classifier that is trained on large datasets of fine-labeled scene images. Whereas at cluttered dynamic scenes such as campus or park, human activities are not strongly confined by rules, and the functional attributes of places are not strongly correlated with objects. So how to define, model and infer scene categories is crucial to make the technique really helpful in assis…
Automatic terrain recognition in Mars rover images is an important problem not just for navigation, but for scientists interested in studying rock types, and by extension, conditions of the ancient Martian paleoclimate and habitability. Existing approaches to label Martian terrain either involve the use of non-expert annotators producing taxonomies of limited granularity (e.g. soil, sand, bedrock, float rock, etc.), or rely on generic class discovery approaches that tend to produce perceptual classes such as rover parts and landscape, which are irrelevant to geologic analysis. Expert-labeled d…
São Paulo State University（圣保罗州立大学）；University of Wolverhampton（伍尔弗汉普顿大学）
Complex wounds usually face partial or total loss of skin thickness, healing by secondary intention. They can be acute or chronic, figuring infections, ischemia and tissue necrosis, and association with systemic diseases. Research institutes around the globe report countless cases, ending up in a severe public health problem, for they involve human resources (e.g., physicians and health care professionals) and negatively impact life quality. This paper presents a new database for automatically categorizing complex wounds with five categories, i.e., non-wound area, granulation, fibrinoid tissue…
Learning Geometric and Photometric Features from Panoramic LiDAR Scans for Outdoor Place Categorization
Graduate School of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电子工程研究生院）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）；Faculty of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电子工程学部）；Technical University of Cartagena（卡塔赫纳技术大学）
University of Washington（华盛顿大学）；Flickr, Yahoo Research（雅虎研究公司Flickr）
In this work, we propose the use of large set of unlabeled images as a source of regularization data for learning robust visual representation. Given a visual model trained by a labeled dataset in a supervised fashion, we augment our training samples by incorporating large number of unlabeled data and train a semi-supervised model. We demonstrate that our proposed learning approach leverages an abundance of unlabeled images and boosts the visual recognition performance which alleviates the need to rely on large labeled datasets for learning robust representation. To increment the number of ima…
Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning
School of Geospatial Engineering and Science, Sun Yat-sen University（中山大学地理空间工程与科学学院）；Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；SenseTime Research（商汤科技研究院）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Chongqing University（重庆大学）；Hong Kong Polytechnic University（香港理工大学）
We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme learning machine based cross-domain network learning framework, that is called Extreme Learning Machine (ELM) based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the l_(2,1)-norm of the network output weights and the learning error simultaneously. The unla…
Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the structured, reusable concepts that help us to rapidly adapt to new tasks and provide reasoning behind our decisions. However, existing meta-learning methods learn complex representations across prior labeled tasks without imposing any structure on the learned representations. Here we propose COMET, a meta-learning method that improves generalization ability …
While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them good at recognizing but poor at localizing objects precisely. This problem is magnified in the context of aerial and satellite image labeling, where a spatially fine object outlining is of paramount importance. Different iterative enhancement algorithms have been presented in the literature to progressively improve the coarse CNN outputs, seeking to sharpen obj…
Sun Yat-sen University（中山大学）；Guangzhou University（广州大学）
Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing active learning methods in two aspects. First, we incorporate deep convolutional neural networks into active learning. Through the properly designed fra…
Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
National University of Singapore (NUS)（新加坡国立大学）；Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局前沿人工智能研究中心）；Institute for Infocomm Research (IR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局信息通信研究所）
Institute of Semiconductors, Chinese Academy of Sciences（中国科学院半导体研究所）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）；Old Dominion University（奥尔多明尼昂大学）；School of Integrated Circuits, University of Chinese Academy of Sciences（中国科学院大学集成电路学院）
