Zero-shot stance detection aims to identify users’ stance without labeled data. This paradigm alleviates the data dependency problem of in-target stance detection and has attracted extensive research. In this article, we propose a novel zero-shot stance detection model consisting of three parts: topic mapping module, sentiment signal extraction module, and contrastive learning module. We introduce sentiment signals to improve the stance detection model performance and use contrastive learning to enhance the learning representation quality. We conducted experiments on the VAST dataset to validate the effectiveness of our proposed method.

Rare critical scenarios are crucial to verify the performance of autonomous driving in different situations. Critical scenario generation requires the ability of sampling critical combinations from an infinite parameter space in the logical scenario. Existing solutions aim to explore the correlation of action parameters in the initial scenario rather than action sequences. How to model action sequences so that one can further consider the effects of different action parameters is the bottleneck of the problem. In this paper, we solve the problem by proposing the ECSAS framework. Specifically, we first propose a description language, BTScenario, allowing us to model action sequences of scenarios. We then use reinforcement learning to search for combinations of critical action parameters. Several optimizations are proposed to increase efficiency, including action mask and replay buffer. Experimental results show that our model with strong collision ability and effectively outperforms the existing methods on various nontrivial scenarios.

With the rise of big data, the quality of datasets has become a crucial factor affecting the performance of machine learning models. High-quality datasets are essential for the realization of data value. This survey article summarizes the research direction of dataset quality in machine learning, including the definition of related concepts, analysis of quality issues and risks, and a review of dataset quality dimensions and metrics throughout the dataset lifecycle and a review of dataset quality metrics analyzed from a dataset lifecycle perspective and summarized in literatures. Furthermore, this article introduces a comprehensive quality evaluation process, which includes a framework for dataset quality evaluation with dimensions and metrics, computation methods for quality metrics, and assessment models. These studies provide valuable guidance for evaluating dataset quality in the field of machine learning, which can help improve the accuracy, efficiency, and generalization ability of machine learning models, and promote the development and application of artificial intelligence technology.

A deep facial attribute editing model strives to meet two requirements: (1) attribute correctness – the target attribute should correctly appear on the edited face image; (2) irrelevance preservation – any irrelevant information (e.g., identity) should not be changed after editing. Meeting both requirements challenges the state-of-the-art works which resort to either spatial attention or latent space factorization. Specifically, the former assume that each attribute has well-defined local support regions; they are often more effective for editing a local attribute than a global one. The latter factorize the latent space of a fixed pretrained GAN into different attribute-relevant parts, but they cannot be trained end-to-end with the GAN, leading to sub-optimal solutions. To overcome these limitations, we propose a novel latent space factorization model, called L2M-GAN, which is learned end-to-end and effective for editing both local and global attributes. The key novel components are: (1) A latent space vector of the GAN is factorized into an attribute-relevant and irrelevant codes with an orthogonality constraint imposed to ensure disentanglement. (2) An attribute-relevant code transformer is learned to manipulate the attribute value; crucially, the transformed code are subject to the same orthogonality constraint. By forcing both the original attribute-relevant latent code and the edited code to be disentangled from any attribute-irrelevant code, our model strikes the perfect balance between attribute correctness and irrelevance preservation. Extensive experiments on CelebA-HQ show that our L2M-GAN achieves significant improvements over the state-of-the-arts.

Semantic segmentation is a fundamental vision problem which aims to divide an image into non-overlapped regions and then assign them with predefined object labels. Despite its latest development (especially deep neural network-based), semantic segmentation is still far from comprehensive understanding of the visual world around us. For example, the obtained object labels are not fine-grained enough for solving more complicated vision tasks such as fine-grained retrieval with multiple attribute-based queries (e.g. the query ‘a bird’ along with the attribute ‘has wing colour: grey’). In this paper, we thus choose to study a more challenging vision problem called attribute segmentation, which aims to localize attributes within the targeted object (e.g. bird) in a given image. Due to the high cost of collecting pixel-level attribute annotations, we focus on weakly-supervised attribute segmentation (WSAS) that utilizes only image-level attribute labels for model training. Note that this new WSAS problem degrades to the conventional weakly-supervised semantic segmentation (WSSS) problem when attribute labels are considered as object labels. To overcome the attribute label noise caused by image-level weak supervision, we propose a novel sparse learning method for solving the WSAS problem. Extensive experiments demonstrate that the proposed WSAS method significantly outperforms the state-of-the-art WSSS and attribute localization methods.

Most recent few-shot learning (FSL) methods are based on meta-learning with episodic training. In each meta-training episode, a discriminative feature embedding and/or classifier are first constructed from a support set in an inner loop, and then evaluated in an outer loop using a query set for model updating. This query set sample centered learning objective is however intrinsically limited in addressing the lack of training data problem in the support set. In this paper, a novel contrastive prototype learning with augmented embeddings (CPLAE) model is proposed to overcome this limitation. First, data augmentations are introduced to both the support and query sets with each sample now being represented as an augmented embedding (AE) composed of concatenated embeddings of both the original and augmented versions. Second, a novel support set class prototype centered contrastive loss is proposed for contrastive prototype learning (CPL). With a class prototype as an anchor, CPL aims to pull the query samples of the same class closer and those of different classes further away. This support set sample centered loss is highly complementary to the existing query centered loss, fully exploiting the limited training data in each episode. Extensive experiments on several benchmarks demonstrate that our proposed CPLAE achieves new state-of-the-art.

Zero-shot learning (ZSL) typically learns a projection function between a feature space and a semantic space (e.g. attribute space) to recognize unseen classes without any training samples. However, when the projection function learned only with seen class training samples is applied to unseen class test samples, most existing ZSL models suffer from projection domain shift. In this paper, we propose a new ZSL model, termed joint inductive learning (JIL) of bidirectional projections and shared subspace, to learn more generalizable projections and thus algin the seen and unseen class domains. By inducing the two tasks of bidirectional projection learning (BPL) and shared subspace learning (SSL), we integrate three forms of projection learning into a unified framework, which makes our JIL model become more generalizable across the two domains. Moreover, since a shared subspace is actually learned between the feature and semantic spaces, our JIL model can be naturally applied to cross-modal retrieval (CMR). Extensive experiments demonstrate that our JIL model generally outperforms the state-of-the-art alternatives in the two challenging tasks (i.e. ZSL and CMR).

This paper investigates the problem of weakly-supervised semantic segmentation, where image-level labels are used as weak supervision. Inspired by the successful use of Convolutional Neural Networks (CNNs) for fully-supervised semantic segmentation, we choose to directly train the CNNs over the oversegmented regions of images for weakly-supervised semantic segmentation. Although there are a few studies on CNNs-based weakly-supervised semantic segmentation, they have rarely considered the noise issue, i.e., the initial weak labels (e.g., social tags) may be noisy. To cope with this issue, we thus propose graph-boosted CNNs (GB-CNNs) for weakly-supervised semantic segmentation. In our GB-CNNs, the graph-based model provides the initial supervision for training the CNNs, and then the outcomes of the CNNs are used to retrain the graph-based model. This training procedure is iteratively implemented to boost the results of semantic segmentation. Experimental results demonstrate that the proposed model outperforms the state-of-the-art weakly-supervised methods. More notably, the proposed model is shown to be more robust in the noisy setting for weakly-supervised semantic segmentation.