Search

Pathological diagnosis remains the definitive standard for identifying tumors. The rise of multimodal large models has simplified the process of integrating image analysis with textual descriptions. Despite this advancement, the substantial costs associated with training and deploying these complex multimodal models, together with a scarcity of high-quality training datasets, create a significant divide between cutting-edge technology and its application in the clinical setting. We had meticulously compiled a dataset of approximately 45,000 cases, covering over 6 different tasks, including the classification of organ tissues, generating pathology report descriptions, and addressing pathology-related questions and answers. We have fine-tuned multimodal large models, specifically LLaVA, Qwen-VL, InternLM, with this dataset to enhance instruction-based performance. We conducted a qualitative assessment of the capabilities of the base model and the fine-tuned model in performing image captioning and classification tasks on the specific dataset. The evaluation results demonstrate that the fine-tuned model exhibits proficiency in addressing typical pathological questions. We hope that by making both our models and datasets publicly available, they can be valuable to the medical and research communities., Comment: 10 pages, 2 figures

We present ControlLLM, a novel framework that enables large language models (LLMs) to utilize multi-modal tools for solving complex real-world tasks. Despite the remarkable performance of LLMs, they still struggle with tool invocation due to ambiguous user prompts, inaccurate tool selection and parameterization, and inefficient tool scheduling. To overcome these challenges, our framework comprises three key components: (1) a \textit{task decomposer} that breaks down a complex task into clear subtasks with well-defined inputs and outputs; (2) a \textit{Thoughts-on-Graph (ToG) paradigm} that searches the optimal solution path on a pre-built tool graph, which specifies the parameter and dependency relations among different tools; and (3) an \textit{execution engine with a rich toolbox} that interprets the solution path and runs the tools efficiently on different computational devices. We evaluate our framework on diverse tasks involving image, audio, and video processing, demonstrating its superior accuracy, efficiency, and versatility compared to existing methods. The code is at https://github.com/OpenGVLab/ControlLLM., Comment: 24 pages, 9 figures, 12 tables

Image recognition and generation have long been developed independently of each other. With the recent trend towards general-purpose representation learning, the development of general representations for both recognition and generation tasks is also promoted. However, preliminary attempts mainly focus on generation performance, but are still inferior on recognition tasks. These methods are modeled in the vector-quantized (VQ) space, whereas leading recognition methods use pixels as inputs. Our key insights are twofold: (1) pixels as inputs are crucial for recognition tasks; (2) VQ tokens as reconstruction targets are beneficial for generation tasks. These observations motivate us to propose an Alternating Denoising Diffusion Process (ADDP) that integrates these two spaces within a single representation learning framework. In each denoising step, our method first decodes pixels from previous VQ tokens, then generates new VQ tokens from the decoded pixels. The diffusion process gradually masks out a portion of VQ tokens to construct the training samples. The learned representations can be used to generate diverse high-fidelity images and also demonstrate excellent transfer performance on recognition tasks. Extensive experiments show that our method achieves competitive performance on unconditional generation, ImageNet classification, COCO detection, and ADE20k segmentation. Importantly, our method represents the first successful development of general representations applicable to both generation and dense recognition tasks. Code is released at \url{https://github.com/ChangyaoTian/ADDP}., Comment: Accepted by ICLR2024

The evolution of semantic segmentation has long been dominated by learning more discriminative image representations for classifying each pixel. Despite the prominent advancements, the priors of segmentation masks themselves, e.g., geometric and semantic constraints, are still under-explored. In this paper, we propose to ameliorate the semantic segmentation quality of existing discriminative approaches with a mask prior modeled by a recently-developed denoising diffusion generative model. Beginning with a unified architecture that adapts diffusion models for mask prior modeling, we focus this work on a specific instantiation with discrete diffusion and identify a variety of key design choices for its successful application. Our exploratory analysis revealed several important findings, including: (1) a simple integration of diffusion models into semantic segmentation is not sufficient, and a poorly-designed diffusion process might lead to degradation in segmentation performance; (2) during the training, the object to which noise is added is more important than the type of noise; (3) during the inference, the strict diffusion denoising scheme may not be essential and can be relaxed to a simpler scheme that even works better. We evaluate the proposed prior modeling with several off-the-shelf segmentors, and our experimental results on ADE20K and Cityscapes demonstrate that our approach could achieve competitively quantitative performance and more appealing visual quality.

Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. However, our research indicates that token-level alignment is also crucial in multilingual scenarios, which has not been fully explored previously. Based on our findings, we propose a dual-alignment pre-training (DAP) framework for cross-lingual sentence embedding that incorporates both sentence-level and token-level alignment. To achieve this, we introduce a novel representation translation learning (RTL) task, where the model learns to use one-side contextualized token representation to reconstruct its translation counterpart. This reconstruction objective encourages the model to embed translation information into the token representation. Compared to other token-level alignment methods such as translation language modeling, RTL is more suitable for dual encoder architectures and is computationally efficient. Extensive experiments on three sentence-level cross-lingual benchmarks demonstrate that our approach can significantly improve sentence embedding. Our code is available at https://github.com/ChillingDream/DAP., Comment: ACL 2023

In continual learning, model needs to continually learn a feature extractor and classifier on a sequence of tasks. This paper focuses on how to learn a classifier based on a pretrained feature extractor under continual learning setting. We present an probabilistic analysis that the failure of vanilla experience replay (ER) comes from unnecessary re-learning of previous tasks and incompetence to distinguish current task from the previous ones, which is the cause of knowledge degradation and prediction bias. To overcome these weaknesses, we propose a novel replay strategy task-aware experience replay. It rebalances the replay loss and detaches classifier weight for the old tasks from the update process, by which the previous knowledge is kept intact and the overfitting on episodic memory is alleviated. Experimental results show our method outperforms current state-of-the-art methods.

Continual learning requires the model to maintain the learned knowledge while learning from a non-i.i.d data stream continually. Due to the single-pass training setting, online continual learning is very challenging, but it is closer to the real-world scenarios where quick adaptation to new data is appealing. In this paper, we focus on online class-incremental learning setting in which new classes emerge over time. Almost all existing methods are replay-based with a softmax classifier. However, the inherent logits bias problem in the softmax classifier is a main cause of catastrophic forgetting while existing solutions are not applicable for online settings. To bypass this problem, we abandon the softmax classifier and propose a novel generative framework based on the feature space. In our framework, a generative classifier which utilizes replay memory is used for inference, and the training objective is a pair-based metric learning loss which is proven theoretically to optimize the feature space in a generative way. In order to improve the ability to learn new data, we further propose a hybrid of generative and discriminative loss to train the model. Extensive experiments on several benchmarks, including newly introduced task-free datasets, show that our method beats a series of state-of-the-art replay-based methods with discriminative classifiers, and reduces catastrophic forgetting consistently with a remarkable margin.

We study a practical setting of continual learning: fine-tuning on a pre-trained model continually. Previous work has found that, when training on new tasks, the features (penultimate layer representations) of previous data will change, called representational shift. Besides the shift of features, we reveal that the intermediate layers' representational shift (IRS) also matters since it disrupts batch normalization, which is another crucial cause of catastrophic forgetting. Motivated by this, we propose ConFiT, a fine-tuning method incorporating two components, cross-convolution batch normalization (Xconv BN) and hierarchical fine-tuning. Xconv BN maintains pre-convolution running means instead of post-convolution, and recovers post-convolution ones before testing, which corrects the inaccurate estimates of means under IRS. Hierarchical fine-tuning leverages a multi-stage strategy to fine-tune the pre-trained network, preventing massive changes in Conv layers and thus alleviating IRS. Experimental results on four datasets show that our method remarkably outperforms several state-of-the-art methods with lower storage overhead.

Purpose: The purpose is to design a novelty automatic diagnostic method for osteoporosis screening by using the potential capability of convolutional neural network (CNN) in feature representation and extraction, which can be incorporated into the procedure of routine CT diagnostic in physical examination thereby improving the osteoporosis diagnosis and reducing the patient burden. Methods: The proposed convolutional neural network-based method mainly comprises two functional modules to perform automatic detection of bone condition by analyzing the diagnostic CT image. The first functional module aims to locate and segment the ROI of diagnostic CT image, called Mark-Segmentation-Network (MS-Net). The second functional module is used to determine the category of bone condition by the features of ROI, called Bone-Conditions-Classification-Network (BCC-Net). The trained MS-Net can get the mark image of inputted original CT image, thereby obtain the segmentation image. The trained BCC-Net can obtain the probability value of normal bone mass, low bone mass, and osteoporosis by inputting the segmentation image. On the basis of network results, the radiologists can provide preliminary qualitative diagnosis results of bone condition. Results: The proposed MS-Net has an excellent segmentation precision on the shape preservation of different lumbar vertebra. The numerical indicators of segmentation results are greater than 0.998. The proposed BCC-Net was evaluated with 3,024 clinical images and achieved an accuracy of 76.65% and an area under the receiver operating characteristic curve of 0.9167. Conclusions: This study proposed a novel two-step method for automatic detection of bone conditions via diagnostic CT images and it has great potential in clinical applications for osteoporosis screening. The method can potentially reduce the manual burden to radiologists and diagnostic cost to patients.

The improvement of computed tomography (CT) image resolution is beneficial to the subsequent medical diagnosis, but it is usually limited by the scanning devices and great expense. Convolutional neural network (CNN)-based methods have achieved promising ability in super-resolution. However, existing methods mainly focus on the super-resolution of reconstructed image and do not fully explored the approach of super-resolution from projection-domain. In this paper, we studied the characteristic of projection and proposed a CNN-based super-resolution method to establish the mapping relationship of low- and high-resolution projection. The network label is high-resolution projection and the input is its corresponding interpolation data after down sampling. FDK algorithm is utilized for three-dimensional image reconstruction and one slice of reconstruction image is taken as an example to evaluate the performance of the proposed method. Qualitative and quantitative results show that the proposed method is potential to improve the resolution of projection and enables the reconstructed image with higher quality.

Limited-angle computed tomography (CT) image reconstruction is a challenging reconstruction problem in the fields of CT. With the development of deep learning, the generative adversarial network (GAN) perform well in image restoration by approximating the distribution of training sample data. In this paper, we proposed an effective GAN-based inpainting method to restore the missing sinogram data for limited-angle scanning. To estimate the missing data, we design the generator and discriminator of the patch-GAN and train the network to learn the data distribution of the sinogram. We obtain the reconstructed image from the restored sinogram by filtered back projection and simultaneous algebraic reconstruction technique with total variation. Experimental results show that serious artifacts caused by missing projection data can be reduced by the proposed method, and it is hopeful to solve the reconstruction problem of 60 degrees limited scanning angle.

The output impedance matrix of a grid-connected converter plays an important role in analyzing system stability. Due to the dynamics of the DC-link control and the phase locked loop (PLL), the output impedance matrices of the converter and grid are difficult to be diagonally decoupled simultaneously, neither in the dq domain nor in the phase domain. It weakens the effectiveness of impedance-based stability criterion (ISC) in system oscillation analysis. To this end, this paper innovatively proposes the generalized-impedance based stability criterion (GISC) to reduce the dimension of the transfer function matrix and simplify system small-signal stability analysis. Firstly, the impedances of the converter and the grid in polar coordinates are formulated, and the concept of generalized-impedance of the converter and the grid is put forward. Secondly, through strict mathematical derivation, the equation that implies the dynamic interaction between the converter and the grid is then extracted from the characteristic equation of the grid-connected converter system. Using the proposed method, the small-signal instability of system can be interpreted as the resonance of the generalized-impedances of the converter and the grid. Besides, the GISC is equivalent to ISC when the dynamics of the outer-loop control and PLL are not considered. Finally, the effectiveness of the proposed method is further verified using the MATLAB based digital simulation and RT-LAB based hardware-in-the-loop (HIL) simulation., Comment: 11 pages

The output impedance matrices of three-phase grid-connected voltage source converters (VSCs) are widely used in power system stability analysis. Regardless of how the impedance is modeled, there always exist coupling terms in the impedance matrix, which makes the system a multi-input- multi-output (MIMO) system. Some approximation approaches omit the coupling terms so that a three-phase system can be treated like a single-phase one, and the impedance-based stability criterion for a single-input-single-output (SISO) system is applicable. However, such handling may result in analytical errors or even incorrect conclusions in a mirror frequency coupled system. By introducing the concept of generalized- impedances, this letter proposes a new stability criterion based on a virtual SISO system, which can effectively handle the coupling terms. Further, the effects of the phase-locked-loop (PLL) parameters on system stability are studied based on the proposed criterion. The effectiveness of the proposed criterion is verified by a hardware-in-the-loop (HIL) simulation based on RT-LAB.