In autonomous driving, 3D lane detection using monocular cameras is an important task for various downstream planning and control tasks. Recent CNN and Transformer approaches usually apply a two-stage scheme in the model design. The first stage transforms the image feature from a front image into a bird's-eye-view (BEV) representation. Subsequently, a sub-network processes the BEV feature map to generate the 3D detection results. However, these approaches heavily rely on a challenging image feature transformation module from a perspective view to a BEV representation. In our work, we present CurveFormer++, a single-stage Transformer-based method that does not require the image feature view transform module and directly infers 3D lane detection results from the perspective image features. Specifically, our approach models the 3D detection task as a curve propagation problem, where each lane is represented by a curve query with a dynamic and ordered anchor point set. By employing a Transformer decoder, the model can iteratively refine the 3D lane detection results. A curve cross-attention module is introduced in the Transformer decoder to calculate similarities between image features and curve queries of lanes. To handle varying lane lengths, we employ context sampling and anchor point restriction techniques to compute more relevant image features for a curve query. Furthermore, we apply a temporal fusion module that incorporates selected informative sparse curve queries and their corresponding anchor point sets to leverage historical lane information. In the experiments, we evaluate our approach for the 3D lane detection task on two publicly available real-world datasets. The results demonstrate that our method provides outstanding performance compared with both CNN and Transformer based methods. We also conduct ablation studies to analyze the impact of each component in our approach.
Existing learning-based solutions to medical image segmentation have two important shortcomings. First, for most new segmentation task, a new model has to be trained or fine-tuned. This requires extensive resources and machine learning expertise, and is therefore often infeasible for medical researchers and clinicians. Second, most existing segmentation methods produce a single deterministic segmentation mask for a given image. In practice however, there is often considerable uncertainty about what constitutes the correct segmentation, and different expert annotators will often segment the same image differently. We tackle both of these problems with Tyche, a model that uses a context set to generate stochastic predictions for previously unseen tasks without the need to retrain. Tyche differs from other in-context segmentation methods in two important ways. (1) We introduce a novel convolution block architecture that enables interactions among predictions. (2) We introduce in-context test-time augmentation, a new mechanism to provide prediction stochasticity. When combined with appropriate model design and loss functions, Tyche can predict a set of plausible diverse segmentation candidates for new or unseen medical images and segmentation tasks without the need to retrain.
Diffusion models have achieved remarkable success in image generation tasks, yet their practical deployment is restrained by the high memory and time consumption. While quantization paves a way for diffusion model compression and acceleration, existing methods totally fail when the models are quantized to low-bits. In this paper, we unravel three properties in quantized diffusion models that compromise the efficacy of current methods: imbalanced activation distributions, imprecise temporal information, and vulnerability to perturbations of specific modules. To alleviate the intensified low-bit quantization difficulty stemming from the distribution imbalance, we propose finetuning the quantized model to better adapt to the activation distribution. Building on this idea, we identify two critical types of quantized layers: those holding vital temporal information and those sensitive to reduced bit-width, and finetune them to mitigate performance degradation with efficiency. We empirically verify that our approach modifies the activation distribution and provides meaningful temporal information, facilitating easier and more accurate quantization. Our method is evaluated over three high-resolution image generation tasks and achieves state-of-the-art performance under various bit-width settings, as well as being the first method to generate readable images on full 4-bit (i.e. W4A4) Stable Diffusion. Code is been made publicly available.
Multi-modality image fusion (MMIF) integrates the complementary information from different modal images to provide comprehensive and objective interpretation of a scenes. However, existing MMIF methods lack the ability to resist different weather interferences in real-life scenarios, preventing them from being useful in practical applications such as autonomous driving. To bridge this research gap, we proposed an all-weather MMIF model. Regarding deep learning architectures, their network designs are often viewed as a black box, which limits their multitasking capabilities. For deweathering module, we propose a physically-aware clear feature prediction module based on an atmospheric scattering model that can deduce variations in light transmittance from both scene illumination and depth. For fusion module, We utilize a learnable low-rank representation model to decompose images into low-rank and sparse components. This highly interpretable feature separation allows us to better observe and understand images. Furthermore, we have established a benchmark for MMIF research under extreme weather conditions. It encompasses multiple scenes under three types of weather: rain, haze, and snow, with each weather condition further subdivided into various impact levels. Extensive fusion experiments under adverse weather demonstrate that the proposed algorithm has excellent detail recovery and multi-modality feature extraction capabilities.
The rapid development of Multi-modality Large Language Models (MLLMs) has navigated a paradigm shift in computer vision, moving towards versatile foundational models. However, evaluating MLLMs in low-level visual perception and understanding remains a yet-to-explore domain. To this end, we design benchmark settings to emulate human language responses related to low-level vision: the low-level visual perception (A1) via visual question answering related to low-level attributes (e.g. clarity, lighting); and the low-level visual description (A2), on evaluating MLLMs for low-level text descriptions. Furthermore, given that pairwise comparison can better avoid ambiguity of responses and has been adopted by many human experiments, we further extend the low-level perception-related question-answering and description evaluations of MLLMs from single images to image pairs. Specifically, for perception (A1), we carry out the LLVisionQA+ dataset, comprising 2,990 single images and 1,999 image pairs each accompanied by an open-ended question about its low-level features; for description (A2), we propose the LLDescribe+ dataset, evaluating MLLMs for low-level descriptions on 499 single images and 450 pairs. Additionally, we evaluate MLLMs on assessment (A3) ability, i.e. predicting score, by employing a softmax-based approach to enable all MLLMs to generate quantifiable quality ratings, tested against human opinions in 7 image quality assessment (IQA) datasets. With 24 MLLMs under evaluation, we demonstrate that several MLLMs have decent low-level visual competencies on single images, but only GPT-4V exhibits higher accuracy on pairwise comparisons than single image evaluations (like humans). We hope that our benchmark will motivate further research into uncovering and enhancing these nascent capabilities of MLLMs. Datasets will be available at https://github.com/Q-Future/Q-Bench.
Reducing a graph while preserving its overall structure is an important problem with many applications. Typically, the reduction approaches either remove edges (sparsification) or merge nodes (coarsening) in an unsupervised way with no specific downstream task in mind. In this paper, we present an approach for subsampling graph structures using an Ising model defined on either the nodes or edges and learning the external magnetic field of the Ising model using a graph neural network. Our approach is task-specific as it can learn how to reduce a graph for a specific downstream task in an end-to-end fashion. The utilized loss function of the task does not even have to be differentiable. We showcase the versatility of our approach on three distinct applications: image segmentation, 3D shape sparsification, and sparse approximate matrix inverse determination.
Automatic colorization of grayscale image has been a challenging task. Previous research have applied supervised methods in conquering this problem [ 1]. In this paper, we reproduces a GAN-based coloring model, and experiments one of its variant. We also proposed a CycleGAN based model and experiments those methods on various datasets. The result shows that the proposed CycleGAN model does well in human-face coloring and comic coloring, but lack the ability to diverse colorization.
This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature of client data, often results in suboptimal personalization of a global model compared to locally trained models for each client. To tackle this challenge, we propose a novel approach named FedD2S for Personalized Federated Learning (pFL), leveraging knowledge distillation. FedD2S incorporates a deep-to-shallow layer-dropping mechanism in the data-free knowledge distillation process to enhance local model personalization. Through extensive simulations on diverse image datasets-FEMNIST, CIFAR10, CINIC0, and CIFAR100-we compare FedD2S with state-of-the-art FL baselines. The proposed approach demonstrates superior performance, characterized by accelerated convergence and improved fairness among clients. The introduced layer-dropping technique effectively captures personalized knowledge, resulting in enhanced performance compared to alternative FL models. Moreover, we investigate the impact of key hyperparameters, such as the participation ratio and layer-dropping rate, providing valuable insights into the optimal configuration for FedD2S. The findings demonstrate the efficacy of adaptive layer-dropping in the knowledge distillation process to achieve enhanced personalization and performance across diverse datasets and tasks.
The rising global prevalence of skin conditions, some of which can escalate to life-threatening stages if not timely diagnosed and treated, presents a significant healthcare challenge. This issue is particularly acute in remote areas where limited access to healthcare often results in delayed treatment, allowing skin diseases to advance to more critical stages. One of the primary challenges in diagnosing skin diseases is their low inter-class variations, as many exhibit similar visual characteristics, making accurate classification challenging. This research introduces a novel multimodal method for classifying skin lesions, integrating smartphone-captured images with essential clinical and demographic information. This approach mimics the diagnostic process employed by medical professionals. A distinctive aspect of this method is the integration of an auxiliary task focused on super-resolution image prediction. This component plays a crucial role in refining visual details and enhancing feature extraction, leading to improved differentiation between classes and, consequently, elevating the overall effectiveness of the model. The experimental evaluations have been conducted using the PAD-UFES20 dataset, applying various deep-learning architectures. The results of these experiments not only demonstrate the effectiveness of the proposed method but also its potential applicability under-resourced healthcare environments.
To address the issue of feature descriptors being ineffective in representing grayscale feature information when images undergo high affine transformations, leading to a rapid decline in feature matching accuracy, this paper proposes a region feature descriptor based on simulating affine transformations using classification. The proposed method initially categorizes images with different affine degrees to simulate affine transformations and generate a new set of images. Subsequently, it calculates neighborhood information for feature points on this new image set. Finally, the descriptor is generated by combining the grayscale histogram of the maximum stable extremal region to which the feature point belongs and the normalized position relative to the grayscale centroid of the feature point's region. Experimental results, comparing feature matching metrics under affine transformation scenarios, demonstrate that the proposed descriptor exhibits higher precision and robustness compared to existing classical descriptors. Additionally, it shows robustness when integrated with other descriptors.