The human cerebral cortex has many bumps and grooves called gyri and sulci. Even though there is a high inter-individual consistency for the main cortical folds, this is not the case when we examine the exact shapes and details of the folding patterns. Because of this complexity, characterizing the cortical folding variability and relating them to subjects' behavioral characteristics or pathologies is still an open scientific problem. Classical approaches include labeling a few specific patterns, either manually or semi-automatically, based on geometric distances, but the recent availability of MRI image datasets of tens of thousands of subjects makes modern deep-learning techniques particularly attractive. Here, we build a self-supervised deep-learning model to detect folding patterns in the cingulate region. We train a contrastive self-supervised model (SimCLR) on both Human Connectome Project (1101 subjects) and UKBioBank (21070 subjects) datasets with topological-based augmentations on the cortical skeletons, which are topological objects that capture the shape of the folds. We explore several backbone architectures (convolutional network, DenseNet, and PointNet) for the SimCLR. For evaluation and testing, we perform a linear classification task on a database manually labeled for the presence of the "double-parallel" folding pattern in the cingulate region, which is related to schizophrenia characteristics. The best model, giving a test AUC of 0.76, is a convolutional network with 6 layers, a 10-dimensional latent space, a linear projection head, and using the branch-clipping augmentation. This is the first time that a self-supervised deep learning model has been applied to cortical skeletons on such a large dataset and quantitatively evaluated. We can now envisage the next step: applying it to other brain regions to detect other biomarkers.
The optimisation of crop harvesting processes for commonly cultivated crops is of great importance in the aim of agricultural industrialisation. Nowadays, the utilisation of machine vision has enabled the automated identification of crops, leading to the enhancement of harvesting efficiency, but challenges still exist. This study presents a new framework that combines two separate architectures of convolutional neural networks (CNNs) in order to simultaneously accomplish the tasks of crop detection and harvesting (robotic manipulation) inside a simulated environment. Crop images in the simulated environment are subjected to random rotations, cropping, brightness, and contrast adjustments to create augmented images for dataset generation. The you only look once algorithmic framework is employed with traditional rectangular bounding boxes for crop localization. The proposed method subsequently utilises the acquired image data via a visual geometry group model in order to reveal the grasping positions for the robotic manipulation.
The unrolling method has been investigated for learning variational models in X-ray computed tomography. However, it has been observed that directly unrolling the regularization model through gradient descent does not produce satisfactory results. In this paper, we present a novel deep learning-based CT reconstruction model, where the low-resolution image is introduced to obtain an effective regularization term for improving the network`s robustness. Our approach involves constructing the backbone network architecture by algorithm unrolling that is realized using the deep equilibrium architecture. We theoretically discuss the convergence of the proposed low-resolution prior equilibrium model and provide the conditions to guarantee convergence. Experimental results on both sparse-view and limited-angle reconstruction problems are provided, demonstrating that our end-to-end low-resolution prior equilibrium model outperforms other state-of-the-art methods in terms of noise reduction, contrast-to-noise ratio, and preservation of edge details.
This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, named NCLR, focuses on 2D-3D neural calibration, a novel pretext task that estimates the rigid transformation aligning camera and LiDAR coordinate systems. First, we propose the learnable transformation alignment to bridge the domain gap between image and point cloud data, converting features into a unified representation space for effective comparison and matching. Second, we identify the overlapping area between the image and point cloud with the fused features. Third, we establish dense 2D-3D correspondences to estimate the rigid transformation. The framework not only learns fine-grained matching from points to pixels but also achieves alignment of the image and point cloud at a holistic level, understanding their relative pose. We demonstrate NCLR's efficacy by applying the pre-trained backbone to downstream tasks, such as LiDAR-based 3D semantic segmentation, object detection, and panoptic segmentation. Comprehensive experiments on various datasets illustrate the superiority of NCLR over existing self-supervised methods. The results confirm that joint learning from different modalities significantly enhances the network's understanding abilities and effectiveness of learned representation. Code will be available at \url{https://github.com/Eaphan/NCLR}.
Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To overcome the limitations of existing approaches regarding generalization and consistency, we introduce a novel neural rendering technique. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Specifically, our method builds neural encoding volumes from generated multi-view inputs. We adjust the weights of the SDF network conditioned on an input image at test-time to allow model adaptation to novel scenes in a feed-forward manner via HyperNetworks. To mitigate artifacts derived from the synthesized views, we propose the use of a volume transformer module to improve the aggregation of image features instead of processing each viewpoint separately. Through our proposed method, dubbed as Hyper-VolTran, we avoid the bottleneck of scene-specific optimization and maintain consistency across the images generated from multiple viewpoints. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
Toon shading is a type of non-photorealistic rendering task of animation. Its primary purpose is to render objects with a flat and stylized appearance. As diffusion models have ascended to the forefront of image synthesis methodologies, this paper delves into an innovative form of toon shading based on diffusion models, aiming to directly render photorealistic videos into anime styles. In video stylization, extant methods encounter persistent challenges, notably in maintaining consistency and achieving high visual quality. In this paper, we model the toon shading problem as four subproblems: stylization, consistency enhancement, structure guidance, and colorization. To address the challenges in video stylization, we propose an effective toon shading approach called \textit{Diffutoon}. Diffutoon is capable of rendering remarkably detailed, high-resolution, and extended-duration videos in anime style. It can also edit the content according to prompts via an additional branch. The efficacy of Diffutoon is evaluated through quantitive metrics and human evaluation. Notably, Diffutoon surpasses both open-source and closed-source baseline approaches in our experiments. Our work is accompanied by the release of both the source code and example videos on Github (Project page: https://ecnu-cilab.github.io/DiffutoonProjectPage/).
Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents. However, there is still a wide gap between the performance of recent MLLM-based applications and the expectation of the broad public, even though the most powerful OpenAI's GPT-4 and Google's Gemini have been deployed. This paper strives to enhance understanding of the gap through the lens of a qualitative study on the generalizability, trustworthiness, and causal reasoning capabilities of recent proprietary and open-source MLLMs across four modalities: ie, text, code, image, and video, ultimately aiming to improve the transparency of MLLMs. We believe these properties are several representative factors that define the reliability of MLLMs, in supporting various downstream applications. To be specific, we evaluate the closed-source GPT-4 and Gemini and 6 open-source LLMs and MLLMs. Overall we evaluate 230 manually designed cases, where the qualitative results are then summarized into 12 scores (ie, 4 modalities times 3 properties). In total, we uncover 14 empirical findings that are useful to understand the capabilities and limitations of both proprietary and open-source MLLMs, towards more reliable downstream multi-modal applications.
Visually Impaired Assistance (VIA) aims to automatically help visually impaired (VI) handle daily activities. The advancement of VIA primarily depends on developments in Computer Vision (CV) and Natural Language Processing (NLP), both of which exhibit cutting-edge paradigms with large models (LMs). Furthermore, LMs have shown exceptional multimodal abilities to tackle challenging physically-grounded tasks such as embodied robots. To investigate the potential and limitations of state-of-the-art (SOTA) LMs' capabilities in VIA applications, we present an extensive study for the task of VIA with LMs (\textbf{VIALM}). In this task, given an \textit{image} illustrating the physical environments and a \textit{linguistic request} from a VI user, VIALM aims to output step-by-step \textit{guidance} to assist the VI user in fulfilling the request grounded in the environment. The study consists of a survey reviewing recent LM research and benchmark experiments examining selected LMs' capabilities in VIA. The results indicate that while LMs can augment VIA, their output cannot be well \textit{grounded} in reality (i.e., 25.7\% GPT-4's responses) and lacks \textit{fine-grained} guidance (i.e., 32.1\% GPT-4's responses).
Few-shot image classification has emerged as a key challenge in the field of computer vision, highlighting the capability to rapidly adapt to new tasks with minimal labeled data. Existing methods predominantly rely on image-level features or local descriptors, often overlooking the holistic context surrounding these descriptors. In this work, we introduce a novel approach termed "Local Descriptor with Contextual Augmentation (LDCA)". Specifically, this method bridges the gap between local and global understanding uniquely by leveraging an adaptive global contextual enhancement module. This module incorporates a visual transformer, endowing local descriptors with contextual awareness capabilities, ranging from broad global perspectives to intricate surrounding nuances. By doing so, LDCA transcends traditional descriptor-based approaches, ensuring each local feature is interpreted within its larger visual narrative. Extensive experiments underscore the efficacy of our method, showing a maximal absolute improvement of 20\% over the next-best on fine-grained classification datasets, thus demonstrating significant advancements in few-shot classification tasks.
Adversarial examples are one critical security threat to various visual applications, where injected human-imperceptible perturbations can confuse the output.Generating transferable adversarial examples in the black-box setting is crucial but challenging in practice. Existing input-diversity-based methods adopt different image transformations, but may be inefficient due to insufficient input diversity and an identical perturbation step size. Motivated by the fact that different image regions have distinctive weights in classification, this paper proposes a black-box adversarial generative framework by jointly designing enhanced input diversity and adaptive step sizes. We design local mixup to randomly mix a group of transformed adversarial images, strengthening the input diversity. For precise adversarial generation, we project the perturbation into the $tanh$ space to relax the boundary constraint. Moreover, the step sizes of different regions can be dynamically adjusted by integrating a second-order momentum.Extensive experiments on ImageNet validate that our framework can achieve superior transferability compared to state-of-the-art baselines.