Joint Input and Output Space Learning for Multi-Label Image Classification

Multi-label image classification is a fundamental but challenging task in computer vision. To tackle the problem, the label-related semantic information is often exploited, but the background context and spatial semantic information of related objects are not fully utilized. To address these issues, a multi-branch deep neural network is proposed in this paper. The first branch is designed to extract the discriminant information from regions of interest to detect target objects. In the second branch, a spatial context-aware approach is proposed to better capture the contextual information of an object in its surroundings by using an adaptive patch expansion mechanism. It helps the detection of small objects that are easily lost without the support of context information. The third one, the object-attentional branch, exploits the spatial semantic relations between the target object and its related objects, to better detect partially occluded, small or dim objects with the support of those easily detectable objects. To better encode such relations, an attention mechanism jointly considering the spatial and semantic relations between objects is developed. Two widely used benchmark datasets for multi-labeling classification, MS COCO and PASCAL VOC, are used to evaluate the proposed framework. The experimental results demonstrate that the proposed method outperforms the state-of-the-art methods for multi-label image classification.

Existing multi-label learning classification algorithms ignore that class labels may be determined by some features in the original feature space. And only a partial label of each instance can be obtained for some real applications. Therefore, we propose a novel algorithm named joint Label-Specific features and Label Correlation for multi-label learning with Missing Label (LSLC-ML) and its optimized version to solve the above-mentioned problems. First, a missing label can be recovered by the learned positive and negative label correlations from the incomplete training data sets, then the label-specific features can be selected, finally the multi-label classification task can be modeled by combining the labelspecific feature selections, missing labels and positive and negative label correlations. The experimental results show that our algorithm LSLC-ML has strong competitiveness compared with some state-of-the-art algorithms in evaluation matrices when tested on benchmark multi-label data sets.

To deal with the problem where each instance is associated with multiple labels, a lot of multi-label learning algorithms have been developed in recent years. Some approaches have been proposed to select label-specific features to utilize discriminate features for multi-label classification. Although label correlation has been considered in learning label-specific features, the critical correlation among instances was less taken into account. In this paper, we proposed a new approach called multi-label learning with label-specific features using correlation information (LSF-CI) to learn label-specific features for each label with the consideration of both correlation information in label space and correlation information in feature space. In the LSF-CI, the instance correlation in feature space is computed by a probabilistic neighborhood graph model, and label correlation in label space is computed by cosine similarity. For multi-label data, the LSF-CI has the capability to select Label-specific features for each label as well as classify an unseen instance into a set of relevant labels. To validate the effectiveness of LSF-CI, we conducted comprehensive experiments on eight multi-label datasets. The experimental results demonstrate that the LSF-CI is capable of selecting compact label-specific features, and achieving a competitive performance in comparison with the performances of the existing multi-label learning approaches.

In multi-label image classification, each image is always associated with multiple labels and labels are usually correlated with each other. The intrinsic relation among labels can definitely contribute to classifier training. However, most previous studies on active learning for multi-label image classification purely mine label correlation based on observed label distribution. They ignore the mapping relation between examples and their labels. This mapping relation also implicates label relationship. Ignoring the mapping relation leads to an uncomprehensive label correlation estimation and results in a bad performance for classification. In this paper, we propose a novel multi-label active learning with low-rank mapping for image classification, called LMMAL, to solve this issue. More precisely, we train a low-rank mapping matrix to signify the mapping relation between the feature space and the label space of a certain multi-label dataset. Using this low-rank mapping relation, we exploit a full label correlation. Subsequently, an effective sampling strategy is designed by integrating this potential information with uncertainty to select the most informative example-label pairs. In addition, we extend LMMAL with automatic labeling (denoted as AL-LMMAL) to further reduce the annotation workload of active learning. Empirical results demonstrate the effectiveness of our approaches.

Most existing work on multi-label learning focused on supervised learning which requires manual annotation samples that is labor-intensive, time-consuming and costly. To address such a problem, we present a novel method that incorporates active learning into the semi-supervised learning for multi-label image classification. What’s more, aiming at the curse of dimensionality existing in high-dimensional data, we explore a dimensionality reduction technique with non-negative sparseness constraint to extract a group of features that can completely describe the data and hence make the learning model more efficiently. Experimental results on common data sets validate that the proposed algorithm is relatively effective to improve the performance of the learner in multi-label classification, and the obtained learner is with reliability and robustness after data dimensionality using NNS-DR (Non-Negative Sparseness for Dimensionality Reduction).

In our daily life, the scenes around us are always with multiple labels especially in a smart city, i.e., recognizing the information of city operation to response and control. Great efforts have been made by using Deep Neural Networks to recognize multi-label images. Since multi-label image classification is very complicated, people seek to use the attention mechanism to guide the classification process. However, conventional attention-based methods always analyzed images directly and aggressively. It is difficult for them to well understand complicated scenes. In this paper, we propose a global/local attention method that can recognize an image from coarse to fine by mimicking how human-beings observe images. Specifically, our global/local attention method first concentrates on the whole image, and then focuses on local specific objects in the image. We also propose a joint max-margin objective function, which enforces that the minimum score of positive labels should be larger than the maximum score of negative labels horizontally and vertically. This function can further improve our multi-label image classification method. We evaluate the effectiveness of our method on two popular multilabel image datasets (i.e., Pascal VOC and MS-COCO). Our experimental results show that our method outperforms state-of-the-art methods.

Multi-Label Image Classification (MLIC) appro-aches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features and lead to model overfitting. In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. PSD decomposes the original MLIC task into several simpler MLIC sub-tasks via two elaborated complementary task decomposition strategies named Co-occurrence Graph Partition (CGP) and Dis-occurrence Graph Partition (DGP). Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels. Finally, knowledge distillation is leveraged to learn a compact global ensemble of full categories with these learned patterns for reconciling the label correlation exploitation and model overfitting. Extensive results on MS-COCO and NUS-WIDE datasets demonstrate that our framework can be easily plugged into many MLIC approaches and improve performances of recent state-of-the-art approaches. The source code is released at https://github.com/Robbie-Xu/CPSD.

Multilabel image classification has been a hot topic in the field of computer vision and image understanding in recent years. To achieve better classification performance with fewer labeled images, multilabel active learning is used for this scenario. Several active learning methods have been proposed for multilabel image classification. However, all of them assume that either all training images have complete labels or label correlations are given at the beginning. These two assumptions are unrealistic. In fact, it is very difficult to obtain complete labels for each example, in particular when the size of labels in a multilabel dataset is very large. Typically, only partial labels are available. This is one type of “weak label” problem. To solve this weak label problem inside multilabel active learning, this paper proposes a novel solution called AE-WLMAL. AE-WLMAL explores conditional label correlations on the weak label problem with the help of input features and then utilizes label correlations to construct a unified sampling strategy and evaluate the informativeness of each example-label pair in a multilabel dataset for active sampling. In addition, a pruning strategy is adopted to further improve its computation efficiency. Moreover, AE-WLAML exploits label correlations to infer labels for unlabeled images, which further reduces human labeling cost. Our experimental results on seven real-world datasets show that AE-WLMAL consistently outperforms existing approaches.

Multi-label image classification is a very challenging task, where data are often associated with multiple labels and represented with multiple views. In this paper, we propose a novel multi-view distance metric learning approach to dealing with the multi-label image classification problem. In particular, we attempt to concatenate multiple types of features after learning one optimal distance metric for each view, so as to obtain a better joint representation across multi-view spaces. To preserve the intrinsic geometric structure of the data in the low-dimensional feature space, we introduce a manifold regularization with the adjacency graph being constructed based on all labels. Moreover, we learn another distance metric to capture the dependency of labels, which can further improve the classification performance. Experimental results on publicly available image datasets demonstrate that our method achieves superior performance, compared with the state-of-the-arts.

In multi-label learning with missing labels, previous works usually only consider all features, or only consider label-specific features. It is obviously inappropriate to select a subset of features only considering which have a great discriminability for all labels or for a label. Besides, they are built on an assumption that if two labels are correlated, their regression coefficient vectors should be similar. However, it is hard to hold this assumption in real-world applications. Therefore, we propose a novel multi-label classification approach for missing labels via considering common and label-specific features with correlation information. More specifically, we firstly utilize <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$l_{1}$</tex> - norm regularizer over label correlation matrix, and a new sup-plementary label matrix is augmented from the incomplete label matrix by learning label correlations. Then, for a better label recovery, we introduce <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$l_{2,1}$</tex> -norm and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$l_{1}$</tex> -norm regularizers to learn common and label-specific features simultaneously. Thirdly, to make more rational use of label correlation to solve missing labels, we use a regularizer to constrain label correlations on outputs of labels instead of regression coefficient matrix. Finally, an objective function is designed in terms of the above processing. Extensive experiments conducted on eight data sets demonstrate the effectiveness of the proposed approach.

Multi-label image classification is crucial for a wide range of multimedia applications. To address the resource limitation issue, various knowledge distillation (KD) methods have been developed to transfer knowledge from a large network (referred to as the "teacher") to a small network (referred to as the "student"). However, existing KD methods do not explicitly distill the dependencies between labels, which limits the model ability to capture multi-label correlation. Furthermore, although existing methods for multi-label image classification have utilized the second-order label pair dependency (direct dependency between two labels), the high-order label pair dependency, which captures the indirect dependency between two labels, remains unexplored. In this paper, we propose a <u>M</u>ulti-Order Label Pair <u>D</u>ependencies <u>K</u>nowledge <u>D</u>istillation (MDKD) framework. MDKD explicitly distills the knowledge to capture multi-order dependencies between labels, including the label pair dependencies from second-order and high-order, thus transferring the insight of label correlations from different perspectives. Extensive experiments on Pascal VOC2007, MSCOCO2014, and NUS-WIDE demonstrate the superior performances of MDKD.

Hierarchical GAN-Tree and Bi-Directional Capsules for multi-label image classification

Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy achieved by top weakly supervised algorithms is still significantly lower than their fully supervised counterparts. In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation. In this pipeline, we first obtain intermediate object localization and pixel labeling results for the training images, and then use such results to train task-specific deep networks in a fully supervised manner. The entire process consists of four stages, including object localization in the training images, filtering and fusing object instances, pixel labeling for the training images, and task-specific network training. To obtain clean object instances in the training images, we propose a novel algorithm for filtering, fusing and classifying object instances collected from multiple solution mechanisms. In this algorithm, we incorporate both metric learning and density-based clustering to filter detected object instances. Experiments show that our weakly supervised pipeline achieves state-of-the-art results in multi-label image classification as well as weakly supervised object detection and very competitive results in weakly supervised semantic segmentation on MS-COCO, PASCAL VOC 2007 and PASCAL VOC 2012.

Multi-label image classification (MLIC) deals with assigning multiple labels to each image, a easy task for human being while still a open problem in machine learning. The greatest challenge in MLIC lies in that different target objects in one image keep distinct viewpoints and scales. One effective way is to borrow the label-related information to guide the selection of interesting region, which will act an important role in classification. By leveraging the attention mechanism in transformer, we propose a region-awared transformer to focus on top related regions and neglect background interference. Furthermore, our approach can cope with the positive-negative imbalance by assigning them different exponential decay factors of positive and negative samples separately. Experiments on MS-COCO show a competitive performance against other state-of-the-art methods.

Partial multi-label learning via specific label disambiguation