The mainstream workflow of image recognition applications is first training one global model on the cloud for a wide range of classes and then serving numerous clients, each with heterogeneous images from a small subset of classes to be recognized. From the cloud-client discrepancies on the range of image classes, the recognition model is desired to have strong adaptiveness, intuitively by concentrating the focus on each individual client's local dynamic class subset, while incurring negligible overhead. In this work, we propose to plug a new intra-client and inter-image attention (ICIIA) module into existing backbone recognition models, requiring only one-time cloud-based training to be client-adaptive. In particular, given a target image from a certain client, ICIIA introduces multi-head self-attention to retrieve relevant images from the client's historical unlabeled images, thereby calibrating the focus and the recognition result. Further considering that ICIIA's overhead is dominated by linear projection, we propose partitioned linear projection with feature shuffling for replacement and allow increasing the number of partitions to dramatically improve efficiency without scarifying too much accuracy. We finally evaluate ICIIA using 3 different recognition tasks with 9 backbone models over 5 representative datasets. Extensive evaluation results demonstrate the effectiveness and efficiency of ICIIA. Specifically, for ImageNet-1K with the backbone models of MobileNetV3-L and Swin-B, ICIIA can improve the testing accuracy to 83.37% (+8.11%) and 88.86% (+5.28%), while adding only 1.62% and 0.02% of FLOPs, respectively.
Uncertainty estimation of the trained deep learning network provides important information for improving the learning efficiency or evaluating the reliability of the network prediction. In this paper, we propose a method for the uncertainty estimation for multi-class image classification using test-time mixup augmentation (TTMA). To improve the discrimination ability between the correct and incorrect prediction of the existing aleatoric uncertainty, we propose the data uncertainty by applying the mixup augmentation on the test data and measuring the entropy of the histogram of predicted labels. In addition to the data uncertainty, we propose a class-specific uncertainty presenting the aleatoric uncertainty associated with the specific class, which can provide information on the class confusion and class similarity of the trained network. The proposed methods are validated on two public datasets, the ISIC-18 skin lesion diagnosis dataset, and the CIFAR-100 real-world image classification dataset. The experiments demonstrate that (1) the proposed data uncertainty better separates the correct and incorrect prediction than the existing uncertainty measures thanks to the mixup perturbation, and (2) the proposed class-specific uncertainty provides information on the class confusion and class similarity of the trained network for both datasets.
Human Action Recognition (HAR) involves the task of categorizing actions present in video sequences. Although it presents interesting problems, it remains one of the most challenging domains in pattern recognition. Convolutional Neural Networks (ConvNets) have demonstrated exceptional success in image recognition and related areas. However, these advanced techniques are not always directly applicable to HAR, as the consideration of temporal features is crucial. In this paper, we present a dynamic PSO-ConvNet model for learning actions in video, drawing on our recent research in image recognition. Our methods are based on a framework where the weight vector of each neural network serves as the position of a particle in phase space, and particles exchange their current weight vectors and gradient estimates of the Loss function. We extend the approach to video by integrating a ConvNet with state-of-the-art temporal methods such as Transformer and Recurrent Neural Networks. The results reveal substantial advancements, with improvements of up to 9% on UCF-101 dataset. The code is available at https://github.com/leonlha/Video-Action-Recognition-via-PSO-ConvNet-Transformer-Collaborative-Learning-with-Dynamics.
Image blending aims to combine multiple images seamlessly. It remains challenging for existing 2D-based methods, especially when input images are misaligned due to differences in 3D camera poses and object shapes. To tackle these issues, we propose a 3D-aware blending method using generative Neural Radiance Fields (NeRF), including two key components: 3D-aware alignment and 3D-aware blending. For 3D-aware alignment, we first estimate the camera pose of the reference image with respect to generative NeRFs and then perform 3D local alignment for each part. To further leverage 3D information of the generative NeRF, we propose 3D-aware blending that directly blends images on the NeRF's latent representation space, rather than raw pixel space. Collectively, our method outperforms existing 2D baselines, as validated by extensive quantitative and qualitative evaluations with FFHQ and AFHQ-Cat.
Federated Learning (FL) with over-the-air computation is susceptible to analog aggregation error due to channel conditions and noise. Excluding devices with weak channels can reduce the aggregation error, but also decreases the amount of training data in FL. In this work, we jointly design the uplink receiver beamforming and device selection in over-the-air FL to maximize the training convergence rate. We propose a new method termed JBFDS, which takes into account the impact of receiver beamforming and device selection on the global loss function at each training round. Our simulation results with real-world image classification demonstrate that the proposed method achieves faster convergence with significantly lower computational complexity than existing alternatives.
We introduce a new method based on nonnegative matrix factorization, Neural NMF, for detecting latent hierarchical structure in data. Datasets with hierarchical structure arise in a wide variety of fields, such as document classification, image processing, and bioinformatics. Neural NMF recursively applies NMF in layers to discover overarching topics encompassing the lower-level features. We derive a backpropagation optimization scheme that allows us to frame hierarchical NMF as a neural network. We test Neural NMF on a synthetic hierarchical dataset, the 20 Newsgroups dataset, and the MyLymeData symptoms dataset. Numerical results demonstrate that Neural NMF outperforms other hierarchical NMF methods on these data sets and offers better learned hierarchical structure and interpretability of topics.
Phase retrieval (PR) concerns the recovery of complex phases from complex magnitudes. We identify the connection between the difficulty level and the number and variety of symmetries in PR problems. We focus on the most difficult far-field PR (FFPR), and propose a novel method using double deep image priors. In realistic evaluation, our method outperforms all competing methods by large margins. As a single-instance method, our method requires no training data and minimal hyperparameter tuning, and hence enjoys good practicality.
We propose an unsupervised image segmentation approach, that combines a variational energy functional and deep convolutional neural networks. The variational part is based on a recent multichannel multiphase Chan-Vese model, which is capable to extract useful information from multiple input images simultaneously. We implement a flexible multiclass segmentation method that divides a given image into $K$ different regions. We use convolutional neural networks (CNNs) targeting a pre-decomposition of the image. By subsequently minimising the segmentation functional, the final segmentation is obtained in a fully unsupervised manner. Special emphasis is given to the extraction of informative feature maps serving as a starting point for the segmentation. The initial results indicate that the proposed method is able to decompose and segment the different regions of various types of images, such as texture and medical images and compare its performance with another multiphase segmentation method.
Autonomous vehicle simulation has the advantage of testing algorithms in various environment variables and scenarios without wasting time and resources, however, there is a visual gap with the real-world. In this paper, we trained DCLGAN to realistically convert the image of the CARLA simulator and evaluated the effect of the Sim2Real conversion focusing on the LKAS (Lane Keeping Assist System) algorithm. In order to avoid the case where the lane is translated distortedly by DCLGAN, we found the optimal training hyperparameter using FSIM (feature-similarity). After training, we built a system that connected the DCLGAN model with CARLA and AV in real-time. Then, we collected data (e.g. images, GPS) and analyzed them using the following four methods. First, image reality was measured with FID, which we verified quantitatively reflects the lane characteristics. CARLA images that passed through DCLGAN had smaller FID values than the original images. Second, lane segmentation accuracy through ENet-SAD was improved by DCLGAN. Third, in the curved route, the case of using DCLGAN drove closer to the center of the lane and had a high success rate. Lastly, in the straight route, DCLGAN improved lane restoring ability after deviating from the center of the lane as much as in reality.
In this paper, we present TEXTure, a novel method for text-guided generation, editing, and transfer of textures for 3D shapes. Leveraging a pretrained depth-to-image diffusion model, TEXTure applies an iterative scheme that paints a 3D model from different viewpoints. Yet, while depth-to-image models can create plausible textures from a single viewpoint, the stochastic nature of the generation process can cause many inconsistencies when texturing an entire 3D object. To tackle these problems, we dynamically define a trimap partitioning of the rendered image into three progression states, and present a novel elaborated diffusion sampling process that uses this trimap representation to generate seamless textures from different views. We then show that one can transfer the generated texture maps to new 3D geometries without requiring explicit surface-to-surface mapping, as well as extract semantic textures from a set of images without requiring any explicit reconstruction. Finally, we show that TEXTure can be used to not only generate new textures but also edit and refine existing textures using either a text prompt or user-provided scribbles. We demonstrate that our TEXTuring method excels at generating, transferring, and editing textures through extensive evaluation, and further close the gap between 2D image generation and 3D texturing.