In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars", i.e. zero-shot or few-shot counting. To this end, we make the following four contributions: (1) We introduce a novel transformer-based architecture for generalised visual object counting, termed as Counting Transformer (CounTR), which explicitly capture the similarity between image patches or with given "exemplars" with the attention mechanism;(2) We adopt a two-stage training regime, that first pre-trains the model with self-supervised learning, and followed by supervised fine-tuning;(3) We propose a simple, scalable pipeline for synthesizing training images with a large number of instances or that from different semantic categories, explicitly forcing the model to make use of the given "exemplars";(4) We conduct thorough ablation studies on the large-scale counting benchmark, e.g. FSC-147, and demonstrate state-of-the-art performance on both zero and few-shot settings.
Despite a growing number of datasets being collected for training 3D object detection models, significant human effort is still required to annotate 3D boxes on LiDAR scans. To automate the annotation and facilitate the production of various customized datasets, we propose an end-to-end multimodal transformer (MTrans) autolabeler, which leverages both LiDAR scans and images to generate precise 3D box annotations from weak 2D bounding boxes. To alleviate the pervasive sparsity problem that hinders existing autolabelers, MTrans densifies the sparse point clouds by generating new 3D points based on 2D image information. With a multi-task design, MTrans segments the foreground/background, densifies LiDAR point clouds, and regresses 3D boxes simultaneously. Experimental results verify the effectiveness of the MTrans for improving the quality of the generated labels. By enriching the sparse point clouds, our method achieves 4.48\% and 4.03\% better 3D AP on KITTI moderate and hard samples, respectively, versus the state-of-the-art autolabeler. MTrans can also be extended to improve the accuracy for 3D object detection, resulting in a remarkable 89.45\% AP on KITTI hard samples. Codes are at \url{https://github.com/Cliu2/MTrans}.
Existing RGB-D SOD methods mainly rely on a symmetric two-stream CNN-based network to extract RGB and depth channel features separately. However, there are two problems with the symmetric conventional network structure: first, the ability of CNN in learning global contexts is limited; second, the symmetric two-stream structure ignores the inherent differences between modalities. In this paper, we propose a Transformer-based asymmetric network (TANet) to tackle the issues mentioned above. We employ the powerful feature extraction capability of Transformer (PVTv2) to extract global semantic information from RGB data and design a lightweight CNN backbone (LWDepthNet) to extract spatial structure information from depth data without pre-training. The asymmetric hybrid encoder (AHE) effectively reduces the number of parameters in the model while increasing speed without sacrificing performance. Then, we design a cross-modal feature fusion module (CMFFM), which enhances and fuses RGB and depth features with each other. Finally, we add edge prediction as an auxiliary task and propose an edge enhancement module (EEM) to generate sharper contours. Extensive experiments demonstrate that our method achieves superior performance over 14 state-of-the-art RGB-D methods on six public datasets. Our code will be released at https://github.com/lc012463/TANet.
Non-convex relaxation methods have been widely used in tensor recovery problems, and compared with convex relaxation methods, can achieve better recovery results. In this paper, a new non-convex function, Minimax Logarithmic Concave Penalty (MLCP) function, is proposed, and some of its intrinsic properties are analyzed, among which it is interesting to find that the Logarithmic function is an upper bound of the MLCP function. The proposed function is generalized to tensor cases, yielding tensor MLCP and weighted tensor $L\gamma$-norm. Consider that its explicit solution cannot be obtained when applying it directly to the tensor recovery problem. Therefore, the corresponding equivalence theorems to solve such problem are given, namely, tensor equivalent MLCP theorem and equivalent weighted tensor $L\gamma$-norm theorem. In addition, we propose two EMLCP-based models for classic tensor recovery problems, namely low-rank tensor completion (LRTC) and tensor robust principal component analysis (TRPCA), and design proximal alternate linearization minimization (PALM) algorithms to solve them individually. Furthermore, based on the Kurdyka-{\L}ojasiwicz property, it is proved that the solution sequence of the proposed algorithm has finite length and converges to the critical point globally. Finally, Extensive experiments show that proposed algorithm achieve good results, and it is confirmed that the MLCP function is indeed better than the Logarithmic function in the minimization problem, which is consistent with the analysis of theoretical properties.
In this paper, an intelligent reflecting surface (IRS) is introduced to assist an unmanned aerial vehicle (UAV) communication system based on non-orthogonal multiple access (NOMA) for serving multiple ground users. We aim to minimize the average total system energy consumption by jointly designing the resource allocation strategy, the three dimensional (3D) trajectory of the UAV, as well as the phase control at the IRS. The design is formulated as a non-convex optimization problem taking into account the maximum tolerable outage probability constraint and the individual minimum data rate requirement. To circumvent the intractability of the design problem due to the altitude-dependent Rician fading in UAV-to-user links, we adopt the deep neural network (DNN) approach to accurately approximate the corresponding effective channel gains, which facilitates the development of a low-complexity suboptimal iterative algorithm via dividing the formulated problem into two subproblems and address them alternatingly. Numerical results demonstrate that the proposed algorithm can converge to an effective solution within a small number of iterations and illustrate some interesting insights: (1) IRS enables a highly flexible UAV's 3D trajectory design via recycling the dissipated radio signal for improving the achievable system data rate and reducing the flight power consumption of the UAV; (2) IRS provides a rich array gain through passive beamforming in the reflection link, which can substantially reduce the required communication power for guaranteeing the required quality-of-service (QoS); (3) Optimizing the altitude of UAV's trajectory can effectively exploit the outage-guaranteed effective channel gain to save the total required communication power enabling power-efficient UAV communications.
The academic literature of social sciences is the literature that records human civilization and studies human social problems. With the large-scale growth of this literature, ways to quickly find existing research on relevant issues have become an urgent demand for researchers. Previous studies, such as SciBERT, have shown that pre-training using domain-specific texts can improve the performance of natural language processing tasks in those fields. However, there is no pre-trained language model for social sciences, so this paper proposes a pre-trained model on many abstracts published in the Social Science Citation Index (SSCI) journals. The models, which are available on Github (https://github.com/S-T-Full-Text-Knowledge-Mining/SSCI-BERT), show excellent performance on discipline classification and abstract structure-function recognition tasks with the social sciences literature.
This paper proposes a multilingual speech synthesis method which combines unsupervised phonetic representations (UPR) and supervised phonetic representations (SPR) to avoid reliance on the pronunciation dictionaries of target languages. In this method, a pretrained wav2vec 2.0 model is adopted to extract UPRs and a language-independent automatic speech recognition (LI-ASR) model is built with a connectionist temporal classification (CTC) loss to extract segment-level SPRs from the audio data of target languages. Then, an acoustic model is designed, which first predicts UPRs and SPRs from texts separately and then combines the predicted UPRs and SPRs to generate mel-spectrograms. The results of our experiments on six languages show that the proposed method outperformed the methods that directly predicted mel-spectrograms from character or phoneme sequences and the ablated models that utilized only UPRs or SPRs.
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations, which might suffer from under- or over-exposed regions and different sources of noise. The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).
The topic of generalizing machine learning models learned on a collection of source domains to unknown target domains is challenging. While many domain generalization (DG) methods have achieved promising results, they primarily rely on the source domains at train-time without manipulating the target domains at test-time. Thus, it is still possible that those methods can overfit to source domains and perform poorly on target domains. Driven by the observation that domains are strongly related to styles, we argue that reducing the gap between source and target styles can boost models' generalizability. To solve the dilemma of having no access to the target domain during training, we introduce Test-time Fourier Style Calibration (TF-Cal) for calibrating the target domain style on the fly during testing. To access styles, we utilize Fourier transformation to decompose features into amplitude (style) features and phase (semantic) features. Furthermore, we present an effective technique to Augment Amplitude Features (AAF) to complement TF-Cal. Extensive experiments on several popular DG benchmarks and a segmentation dataset for medical images demonstrate that our method outperforms state-of-the-art methods.