Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a task-based information gap to decrease the performance, since the object features in detection task are suboptimal representation and cannot provide all necessary information for subsequent text generation. Besides, object features are usually represented by the last layer features that lose the local details of input images. In this paper, we propose a novel One-Stage Image Captioner (OSIC) with dynamic multi-sight learning, which directly transforms input image into descriptive sentences in one stage. As a result, the task-based information gap can be greatly reduced. To obtain rich features, we use the Swin Transformer to calculate multi-level features, and then feed them into a novel dynamic multi-sight embedding module to exploit both global structure and local texture of input images. To enhance the global modeling of encoder for caption, we propose a new dual-dimensional refining module to non-locally model the interaction of the embedded features. Finally, OSIC can obtain rich and useful information to improve the image caption task. Extensive comparisons on benchmark MS-COCO dataset verified the superior performance of our method.
The traditional centralized baseband processing architecture is faced with the bottlenecks of high computation complexity and excessive fronthaul communication, especially when the number of antennas at the base station (BS) is large. To cope with these two challenges, the decentralized baseband processing (DPB) architecture has been proposed, where the BS antennas are partitioned into multiple clusters, and each is connected to a local baseband unit (BBU). In this paper, we are interested in the low-complexity distributed channel estimation (CE) method under such DBP architecture, which is rarely studied in the literature. The aim is to devise distributed CE algorithms that can perform as well as the centralized scheme but with a small inter-BBU communication cost. Specifically, based on the low-complexity diagonal minimum mean square error channel estimator, we propose two distributed CE algorithms, namely the aggregate-then-estimate algorithm and the estimate-then-aggregate algorithm. In contrast to the existing distributed CE algorithm which requires iterative information exchanges among the nodes, our algorithms only require one roundtrip communication among BBUs. Extensive experiment results are presented to demonstrate the advantages of the proposed distributed CE algorithms in terms of estimation accuracy, inter-BBU communication cost, and computation complexity.
Image guided depth completion aims to recover per-pixel dense depth maps from sparse depth measurements with the help of aligned color images, which has a wide range of applications from robotics to autonomous driving. However, the 3D nature of sparse-to-dense depth completion has not been fully explored by previous methods. In this work, we propose a Graph Convolution based Spatial Propagation Network (GraphCSPN) as a general approach for depth completion. First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning. In addition, the proposed networks explicitly incorporate learnable geometric constraints to regularize the propagation process performed in three-dimensional space rather than in two-dimensional plane. Furthermore, we construct the graph utilizing sequences of feature patches, and update it dynamically with an edge attention module during propagation, so as to better capture both the local neighboring features and global relationships over long distance. Extensive experiments on both indoor NYU-Depth-v2 and outdoor KITTI datasets demonstrate that our method achieves the state-of-the-art performance, especially when compared in the case of using only a few propagation steps. Code and models are available at the project page.
In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection. However, the SOTA bottom-up methods' accuracy is still inferior compared to the existing top-down methods. This is due to the predicted human poses being regressed based on the inconsistent human bounding box center and the lack of human-scale normalization, leading to the predicted human poses being inaccurate and small-scale persons being missed. To push the envelope of the bottom-up pose estimation, we firstly propose multi-scale training to enhance the network to handle scale variation with single-scale testing, particularly for small-scale persons. Secondly, we introduce dual anatomical centers (i.e., head and body), where we can predict the human poses more accurately and reliably, especially for small-scale persons. Moreover, existing bottom-up methods use multi-scale testing to boost the accuracy of pose estimation at the price of multiple additional forward passes, which weakens the efficiency of bottom-up methods, the core strength compared to top-down methods. By contrast, our multi-scale training enables the model to predict high-quality poses in a single forward pass (i.e., single-scale testing). Our method achieves 38.4\% improvement on bounding box precision and 39.1\% improvement on bounding box recall over the state of the art (SOTA) on the challenging small-scale persons subset of COCO. For the human pose AP evaluation, we achieve a new SOTA (71.0 AP) on the COCO test-dev set with the single-scale testing. We also achieve the top performance (40.3 AP) on OCHuman dataset in cross-dataset evaluation.
Empathy is a trait that naturally manifests in human conversation. Theoretically, the birth of empathetic responses results from conscious alignment and interaction between cognition and affection of empathy. However, existing works rely solely on a single affective aspect or model cognition and affection independently, limiting the empathetic capabilities of the generated responses. To this end, based on the commonsense cognition graph and emotional concept graph constructed involving commonsense and concept knowledge, we design a two-level strategy to align coarse-grained (between contextual cognition and contextual emotional state) and fine-grained (between each specific cognition and corresponding emotional reaction) Cognition and Affection for reSponding Empathetically (CASE). Extensive experiments demonstrate that CASE outperforms the state-of-the-art baselines on automatic and human evaluation. Our code will be released.
We introduce the task of microblog opinion summarisation (MOS) and share a dataset of 3100 gold-standard opinion summaries to facilitate research in this domain. The dataset contains summaries of tweets spanning a 2-year period and covers more topics than any other public Twitter summarisation dataset. Summaries are abstractive in nature and have been created by journalists skilled in summarising news articles following a template separating factual information (main story) from author opinions. Our method differs from previous work on generating gold-standard summaries from social media, which usually involves selecting representative posts and thus favours extractive summarisation models. To showcase the dataset's utility and challenges, we benchmark a range of abstractive and extractive state-of-the-art summarisation models and achieve good performance, with the former outperforming the latter. We also show that fine-tuning is necessary to improve performance and investigate the benefits of using different sample sizes.
Instance discrimination contrastive learning (CL) has achieved significant success in learning transferable representations. A hardness-aware property related to the temperature $ \tau $ of the CL loss is identified to play an essential role in automatically concentrating on hard negative samples. However, previous work also proves that there exists a uniformity-tolerance dilemma (UTD) in CL loss, which will lead to unexpected performance degradation. Specifically, a smaller temperature helps to learn separable embeddings but has less tolerance to semantically related samples, which may result in suboptimal embedding space, and vice versa. In this paper, we propose a Model-Aware Contrastive Learning (MACL) strategy to escape UTD. For the undertrained phases, there is less possibility that the high similarity region of the anchor contains latent positive samples. Thus, adopting a small temperature in these stages can impose larger penalty strength on hard negative samples to improve the discrimination of the CL model. In contrast, a larger temperature in the well-trained phases helps to explore semantic structures due to more tolerance to potential positive samples. During implementation, the temperature in MACL is designed to be adaptive to the alignment property that reflects the confidence of a CL model. Furthermore, we reexamine why contrastive learning requires a large number of negative samples in a unified gradient reduction perspective. Based on MACL and these analyses, a new CL loss is proposed in this work to improve the learned representations and training with small batch size.
Recently, many semi-supervised object detection (SSOD) methods adopt teacher-student framework and have achieved state-of-the-art results. However, the teacher network is tightly coupled with the student network since the teacher is an exponential moving average (EMA) of the student, which causes a performance bottleneck. To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2. Based on these networks, a cycle self-training mechanism is built, i.e., S1${\rightarrow}$T1${\rightarrow}$S2${\rightarrow}$T2${\rightarrow}$S1. For S${\rightarrow}$T, we also utilize the EMA weights of the students to update the teachers. For T${\rightarrow}$S, instead of providing supervision for its own student S1(S2) directly, the teacher T1(T2) generates pseudo-labels for the student S2(S1), which looses the coupling effect. Moreover, owing to the property of EMA, the teacher is most likely to accumulate the biases from the student and make the mistakes irreversible. To mitigate the problem, we also propose a distribution consistency reweighting strategy, where pseudo-labels are reweighted based on distribution consistency across the teachers T1 and T2. With the strategy, the two students S2 and S1 can be trained robustly with noisy pseudo labels to avoid confirmation biases. Extensive experiments prove the superiority of CST by consistently improving the AP over the baseline and outperforming state-of-the-art methods by 2.1% absolute AP improvements with scarce labeled data.
The optical fiber network has become a worldwide infrastructure. In addition to the basic functions in telecommunication, its sensing ability has attracted more and more attention. In this paper, we discuss the risk of household fiber being used for eavesdropping and demonstrate its performance in the lab. Using a 3-meter tail fiber in front of the household optical modem, voices of normal human speech can be eavesdropped by a laser interferometer and recovered 1.1 km away. The detection distance limit and system noise are analyzed quantitatively. We also give some practical ways to prevent eavesdropping through household fiber.
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a diversity of novel pretraining tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data hubs. To address this challenge, we introduce BigBIO a community library of 126+ biomedical NLP datasets, currently covering 12 task categories and 10+ languages. BigBIO facilitates reproducible meta-dataset curation via programmatic access to datasets and their metadata, and is compatible with current platforms for prompt engineering and end-to-end few/zero shot language model evaluation. We discuss our process for task schema harmonization, data auditing, contribution guidelines, and outline two illustrative use cases: zero-shot evaluation of biomedical prompts and large-scale, multi-task learning. BigBIO is an ongoing community effort and is available at https://github.com/bigscience-workshop/biomedical