Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper, we empirically prove that the training algorithm and the adaptation algorithm can be completely disentangled, which allows algorithm analysis and design to be done individually for each phase. Our meta-analysis for each phase reveals several interesting insights that may help better understand key aspects of few-shot classification and connections with other fields such as visual representation learning and transfer learning. We hope the insights and research challenges revealed in this paper can inspire future work in related directions.
Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for multi-modal pretraining, which can benefit from modality collaboration while addressing the problem of modality entanglement. In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement. It is flexible to select different modules for different understanding and generation tasks across all modalities including text, image, and video. Empirical study shows that mPLUG-2 achieves state-of-the-art or competitive results on a broad range of over 30 downstream tasks, spanning multi-modal tasks of image-text and video-text understanding and generation, and uni-modal tasks of text-only, image-only, and video-only understanding. Notably, mPLUG-2 shows new state-of-the-art results of 48.0 top-1 accuracy and 80.3 CIDEr on the challenging MSRVTT video QA and video caption tasks with a far smaller model size and data scale. It also demonstrates strong zero-shot transferability on vision-language and video-language tasks. Code and models will be released in https://github.com/alibaba/AliceMind.
Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus not fully exploiting the unique characteristic of video, i.e., temporal. In this paper, we propose a Hierarchical Temporal-Aware video-language pre-training framework, HiTeA, with two novel pre-training tasks for modeling cross-modal alignment between moments and texts as well as the temporal relations of video-text pairs. Specifically, we propose a cross-modal moment exploration task to explore moments in videos, which results in detailed video moment representation. Besides, the inherent temporal relations are captured by aligning video-text pairs as a whole in different time resolutions with multi-modal temporal relation exploration task. Furthermore, we introduce the shuffling test to evaluate the temporal reliance of datasets and video-language pre-training models. We achieve state-of-the-art results on 15 well-established video-language understanding and generation tasks, especially on temporal-oriented datasets (e.g., SSv2-Template and SSv2-Label) with 8.6% and 11.1% improvement respectively. HiTeA also demonstrates strong generalization ability when directly transferred to downstream tasks in a zero-shot manner. Models and demo will be available on ModelScope.
Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications. Intelligent computing has greatly broadened the scope of computing, extending it from traditional computing on data to increasingly diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. Intelligence and computing have undergone paths of different evolution and development for a long time but have become increasingly intertwined in recent years: intelligent computing is not only intelligence-oriented but also intelligence-driven. Such cross-fertilization has prompted the emergence and rapid advancement of intelligent computing. Intelligent computing is still in its infancy and an abundance of innovations in the theories, systems, and applications of intelligent computing are expected to occur soon. We present the first comprehensive survey of literature on intelligent computing, covering its theory fundamentals, the technological fusion of intelligence and computing, important applications, challenges, and future perspectives. We believe that this survey is highly timely and will provide a comprehensive reference and cast valuable insights into intelligent computing for academic and industrial researchers and practitioners.
CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks like zero-shot image captioning remains unsatisfied. In this work, we discuss that directly employing CLIP for zero-shot image captioning relies more on the textual modality in context and largely ignores the visual information, which we call \emph{contextual language prior}. To address this, we propose Cross-modal Language Models (CLMs) to facilitate unsupervised cross-modal learning. We further propose Anchor Augment to guide the generative model's attention to the fine-grained information in the representation of CLIP. Experiments on MS COCO and Flickr 30K validate the promising performance of proposed approach in both captioning quality and computational efficiency.
Although the Conditional Variational AutoEncoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question. A causal analysis is carried out to study the reasons behind, and a methodology of searching for the mediators and mitigating the confounding bias in dialogues is provided. Specifically, we propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediators into generating process. Besides, a dynamic topic graph guided conditional variational autoencoder (TGG-CVAE) model is utilized to complement the semantic space and reduce the confounding bias in responses. Extensive experiments demonstrate that the proposed model is able to generate both relevant and informative responses, and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.
Features, logits, and labels are the three primary data when a sample passes through a deep neural network. Feature perturbation and label perturbation receive increasing attention in recent years. They have been proven to be useful in various deep learning approaches. For example, (adversarial) feature perturbation can improve the robustness or even generalization capability of learned models. However, limited studies have explicitly explored for the perturbation of logit vectors. This work discusses several existing methods related to class-level logit perturbation. A unified viewpoint between positive/negative data augmentation and loss variations incurred by logit perturbation is established. A theoretical analysis is provided to illuminate why class-level logit perturbation is useful. Accordingly, new methodologies are proposed to explicitly learn to perturb logits for both single-label and multi-label classification tasks. Extensive experiments on benchmark image classification data sets and their long-tail versions indicated the competitive performance of our learning method. As it only perturbs on logit, it can be used as a plug-in to fuse with any existing classification algorithms. All the codes are available at https://github.com/limengyang1992/lpl.
Multi-agent exploration of a bounded 3D environment with unknown initial positions of agents is a challenging problem. It requires quickly exploring the environments as well as robustly merging the sub-maps built by the agents. We take the view that the existing approaches are either aggressive or conservative: Aggressive strategies merge two sub-maps built by different agents together when overlap is detected, which can lead to incorrect merging due to the false-positive detection of the overlap and is thus not robust. Conservative strategies direct one agent to revisit an excessive amount of the historical trajectory of another agent for verification before merging, which can lower the exploration efficiency due to the repeated exploration of the same space. To intelligently balance the robustness of sub-map merging and exploration efficiency, we develop a new approach for lidar-based multi-agent exploration, which can direct one agent to repeat another agent's trajectory in an \emph{adaptive} manner based on the quality indicator of the sub-map merging process. Additionally, our approach extends the recent single-agent hierarchical exploration strategy to multiple agents in a \emph{cooperative} manner by planning for agents with merged sub-maps together to further improve exploration efficiency. Our experiments show that our approach is up to 50\% more efficient than the baselines on average while merging sub-maps robustly.
Customer reviews usually contain much information about one's online shopping experience. While positive reviews are beneficial to the stores, negative ones will largely influence consumers' decision and may lead to a decline in sales. Therefore, it is of vital importance to carefully and persuasively reply to each negative review and minimize its disadvantageous effect. Recent studies consider leveraging generation models to help the sellers respond. However, this problem is not well-addressed as the reviews may contain multiple aspects of issues which should be resolved accordingly and persuasively. In this work, we propose a Multi-Source Multi-Aspect Attentive Generation model for persuasive response generation. Various sources of information are appropriately obtained and leveraged by the proposed model for generating more informative and persuasive responses. A multi-aspect attentive network is proposed to automatically attend to different aspects in a review and ensure most of the issues are tackled. Extensive experiments on two real-world datasets, demonstrate that our approach outperforms the state-of-the-art methods and online tests prove that our deployed system significantly enhances the efficiency of the stores' dealing with negative reviews.