Utilizing potent representations of the large vision-language models (VLMs) to accomplish various downstream tasks has attracted increasing attention. Within this research field, soft prompt learning has become a representative approach for efficiently adapting VLMs such as CLIP, to tasks like image classification. However, most existing prompt learning methods learn text tokens that are unexplainable, which cannot satisfy the stringent interpretability requirements of Explainable Artificial Intelligence (XAI) in high-stakes scenarios like healthcare. To address this issue, we propose a novel explainable prompt learning framework that leverages medical knowledge by aligning the semantics of images, learnable prompts, and clinical concept-driven prompts at multiple granularities. Moreover, our framework addresses the lack of valuable concept annotations by eliciting knowledge from large language models and offers both visual and textual explanations for the prompts. Extensive experiments and explainability analyses conducted on various datasets, with and without concept labels, demonstrate that our method simultaneously achieves superior diagnostic performance, flexibility, and interpretability, shedding light on the effectiveness of foundation models in facilitating XAI. The code will be made publically available.
Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their application in vision tasks has not markedly surpassed the performance of traditional Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). This paper posits that the key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling. Traditional ViM approaches, which flatten spatial tokens, overlook the preservation of local 2D dependencies, thereby elongating the distance between adjacent tokens. We introduce a novel local scanning strategy that divides images into distinct windows, effectively capturing local dependencies while maintaining a global perspective. Additionally, acknowledging the varying preferences for scan patterns across different network layers, we propose a dynamic method to independently search for the optimal scan choices for each layer, substantially improving performance. Extensive experiments across both plain and hierarchical models underscore our approach's superiority in effectively capturing image representations. For example, our model significantly outperforms Vim-Ti by 3.1% on ImageNet with the same 1.5G FLOPs. Code is available at: https://github.com/hunto/LocalMamba.
Current human pose estimation systems focus on retrieving an accurate 3D global estimate of a single person. Therefore, this paper presents one of the first 3D multi-person human pose estimation systems that is able to work in real-time and is also able to handle basic forms of occlusion. First, we adjust an off-the-shelf 2D detector and an unsupervised 2D-3D lifting model for use with a 360$^\circ$ panoramic camera and mmWave radar sensors. We then introduce several contributions, including camera and radar calibrations, and the improved matching of people within the image and radar space. The system addresses both the depth and scale ambiguity problems by employing a lightweight 2D-3D pose lifting algorithm that is able to work in real-time while exhibiting accurate performance in both indoor and outdoor environments which offers both an affordable and scalable solution. Notably, our system's time complexity remains nearly constant irrespective of the number of detected individuals, achieving a frame rate of approximately 7-8 fps on a laptop with a commercial-grade GPU.
Current image-based crowd counting widely employs density map regression due to its promising results. However, the method often suffers from severe performance degradation when tested on data from unseen scenarios. To address this so-called "domain shift" problem, we investigate single domain generalization (SDG) for crowd counting. The existing SDG approaches are mainly for classification and segmentation, and can hardly be extended to our case due to its regression nature and label ambiguity (i.e., ambiguous pixel-level ground truths). We propose MPCount, a novel SDG approach effective even for narrow source distribution. Reconstructing diverse features for density map regression with a single memory bank, MPCount retains only domain-invariant representations using a content error mask and attention consistency loss. It further introduces patch-wise classification as an auxiliary task to boost the robustness of density prediction to achieve highly accurate labels. Through extensive experiments on different datasets, MPCount is shown to significantly improve counting accuracy compared to the state of the art under diverse scenarios unobserved in the training data of narrow source distribution. Code is available at https://github.com/Shimmer93/MPCount.
In this paper, we propose \textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This innovation addresses a critical limitation in existing MLLMs: their reliance on a text-only codebook, which restricts MLLM's ability to generate images and texts in a multimodal context. Towards this end, we propose a language-driven iterative training paradigm, coupled with an in-context pre-training task we term ``image decompression'', enabling our model to interpret compressed visual data and generate high-quality images.The unified codebook empowers our model to extend visual instruction tuning to non-linguistic generation tasks. Moreover, UniCode is adaptable to diverse stacked quantization approaches in order to compress visual signals into a more compact token representation. Despite using significantly fewer parameters and less data during training, Unicode demonstrates promising capabilities in visual reconstruction and generation. It also achieves performances comparable to leading MLLMs across a spectrum of VQA benchmarks.
Uninterrupted optical image time series are crucial for the timely monitoring of agricultural land changes. However, the continuity of such time series is often disrupted by clouds. In response to this challenge, we propose a deep learning method that integrates cloud-free optical (Sentinel-2) observations and weather-independent (Sentinel-1) Synthetic Aperture Radar (SAR) data, using a combined Convolutional Neural Network (CNN)-Recurrent Neural Network (RNN) architecture to generate continuous Normalized Difference Vegetation Index (NDVI) time series. We emphasize the significance of observation continuity by assessing the impact of the generated time series on the detection of grassland mowing events. We focus on Lithuania, a country characterized by extensive cloud coverage, and compare our approach with alternative interpolation techniques (i.e., linear, Akima, quadratic). Our method surpasses these techniques, with an average MAE of 0.024 and R^2 of 0.92. It not only improves the accuracy of event detection tasks by employing a continuous time series, but also effectively filters out sudden shifts and noise originating from cloudy observations that cloud masks often fail to detect.
Segmentation of brain structures on MRI is the primary step for further quantitative analysis of brain diseases. Manual segmentation is still considered the gold standard in terms of accuracy; however, such data is extremely time-consuming to generate. This paper presents a deep learning-based segmentation approach for 12 deep-brain structures, utilizing multiple region-based U-Nets. The brain is divided into three focal regions of interest that encompass the brainstem, the ventricular system, and the striatum. Next, three region-based U-nets are run in parallel to parcellate these larger structures into their respective four substructures. This approach not only greatly reduces the training and processing times but also significantly enhances the segmentation accuracy, compared to segmenting the entire MRI image at once. Our approach achieves remarkable accuracy with an average Dice Similarity Coefficient (DSC) of 0.901 and 95% Hausdorff Distance (HD95) of 1.155 mm. The method was compared with state-of-the-art segmentation approaches, demonstrating a high level of accuracy and robustness of the proposed method.
Recent advancements in deep learning have significantly improved brain tumour segmentation techniques; however, the results still lack confidence and robustness as they solely consider image data without biophysical priors or pathological information. Integrating biophysics-informed regularisation is one effective way to change this situation, as it provides an prior regularisation for automated end-to-end learning. In this paper, we propose a novel approach that designs brain tumour growth Partial Differential Equation (PDE) models as a regularisation with deep learning, operational with any network model. Our method introduces tumour growth PDE models directly into the segmentation process, improving accuracy and robustness, especially in data-scarce scenarios. This system estimates tumour cell density using a periodic activation function. By effectively integrating this estimation with biophysical models, we achieve a better capture of tumour characteristics. This approach not only aligns the segmentation closer to actual biological behaviour but also strengthens the model's performance under limited data conditions. We demonstrate the effectiveness of our framework through extensive experiments on the BraTS 2023 dataset, showcasing significant improvements in both precision and reliability of tumour segmentation.
We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise the 3D model. Our key contribution is multi-view consistent editing, which enables editing all images together instead of iteratively editing one image while updating the 3D model as in previous works. It leads to faster editing as well as higher visual quality. This is achieved by the two terms: (a) depth-conditioned editing that enforces geometric consistency across multi-view images by leveraging naturally consistent depth maps. (b) attention-based latent code alignment that unifies the appearance of edited images by conditioning their editing to several reference views through self and cross-view attention between images' latent representations. Experiments demonstrate that our method achieves faster editing and better visual results than previous state-of-the-art methods.
The ability to construct concise scene representations from sensor input is central to the field of robotics. This paper addresses the problem of robustly creating a 3D representation of a tabletop scene from a segmented RGB-D image. These representations are then critical for a range of downstream manipulation tasks. Many previous attempts to tackle this problem do not capture accurate uncertainty, which is required to subsequently produce safe motion plans. In this paper, we cast the representation of 3D tabletop scenes as a multi-class classification problem. To tackle this, we introduce V-PRISM, a framework and method for robustly creating probabilistic 3D segmentation maps of tabletop scenes. Our maps contain both occupancy estimates, segmentation information, and principled uncertainty measures. We evaluate the robustness of our method in (1) procedurally generated scenes using open-source object datasets, and (2) real-world tabletop data collected from a depth camera. Our experiments show that our approach outperforms alternative continuous reconstruction approaches that do not explicitly reason about objects in a multi-class formulation.