ARMOR v0.1: Empowering Autoregressive Multimodal Understanding Model with Interleaved Multimodal Generation via Asymmetric Synergy

Unified models (UniMs) for multimodal understanding and generation have recently received much attention in the area of vision and language. Existing UniMs are designed to simultaneously learn both multimodal understanding and generation capabilities, demanding substantial computational resources, and often struggle to generate interleaved text-image. We present ARMOR, a resource-efficient and pure autoregressive framework that achieves both understanding and generation by fine-tuning existing multimodal large language models (MLLMs). Specifically, ARMOR extends existing MLLMs from three perspectives: (1) For model architecture, an asymmetric encoder-decoder architecture with a forward-switching mechanism is introduced to unify embedding space integrating textual and visual modalities for enabling natural text-image interleaved generation with minimal computational overhead. (2) For training data, a meticulously curated, high-quality interleaved dataset is collected for fine-tuning MLLMs. (3) For the training algorithm, we propose a ``what or how to generate" algorithm to empower existing MLLMs with multimodal generation capabilities while preserving their multimodal understanding capabilities, through three progressive training stages based on the collected dataset. Experimental results demonstrate that ARMOR upgrades existing MLLMs to UniMs with promising image generation capabilities, using limited training resources. Our code will be released soon at https://armor.github.io.

Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection

Owing to large-scale image-text contrastive training, pre-trained vision language model (VLM) like CLIP shows superior open-vocabulary recognition ability. Most existing open-vocabulary object detectors attempt to utilize the pre-trained VLM to attain generative representation. F-ViT uses the pre-trained visual encoder as the backbone network and freezes it during training. However, the frozen backbone doesn't benefit from the labeled data to strengthen the representation. Therefore, we propose a novel two-branch backbone network design, named as ViT-Feature-Modulated Multi-Scale Convolutional network (VMCNet). VMCNet consists of a trainable convolutional branch, a frozen pre-trained ViT branch and a feature modulation module. The trainable CNN branch could be optimized with labeled data while the frozen pre-trained ViT branch could keep the representation ability derived from large-scale pre-training. Then, the proposed feature modulation module could modulate the multi-scale CNN features with the representations from ViT branch. With the proposed mixed structure, detector is more likely to discover novel categories. Evaluated on two popular benchmarks, our method boosts the detection performance on novel category and outperforms the baseline. On OV-COCO, the proposed method achieves 44.3 AP$_{50}^{\mathrm{novel}}$ with ViT-B/16 and 48.5 AP$_{50}^{\mathrm{novel}}$ with ViT-L/14. On OV-LVIS, VMCNet with ViT-B/16 and ViT-L/14 reaches 27.8 and 38.4 mAP$_{r}$.

PSFHS Challenge Report: Pubic Symphysis and Fetal Head Segmentation from Intrapartum Ultrasound Images

Segmentation of the fetal and maternal structures, particularly intrapartum ultrasound imaging as advocated by the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) for monitoring labor progression, is a crucial first step for quantitative diagnosis and clinical decision-making. This requires specialized analysis by obstetrics professionals, in a task that i) is highly time- and cost-consuming and ii) often yields inconsistent results. The utility of automatic segmentation algorithms for biometry has been proven, though existing results remain suboptimal. To push forward advancements in this area, the Grand Challenge on Pubic Symphysis-Fetal Head Segmentation (PSFHS) was held alongside the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023). This challenge aimed to enhance the development of automatic segmentation algorithms at an international scale, providing the largest dataset to date with 5,101 intrapartum ultrasound images collected from two ultrasound machines across three hospitals from two institutions. The scientific community's enthusiastic participation led to the selection of the top 8 out of 179 entries from 193 registrants in the initial phase to proceed to the competition's second stage. These algorithms have elevated the state-of-the-art in automatic PSFHS from intrapartum ultrasound images. A thorough analysis of the results pinpointed ongoing challenges in the field and outlined recommendations for future work. The top solutions and the complete dataset remain publicly available, fostering further advancements in automatic segmentation and biometry for intrapartum ultrasound imaging.

VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-Tuning

Recent advances in Large Vision-Language Models (LVLMs) have significantly improve performance in image comprehension tasks, such as formatted charts and rich-content images. Yet, Graphical User Interface (GUI) pose a greater challenge due to their structured format and detailed textual information. Existing LVLMs often overly depend on internal knowledge and neglect image content, resulting in hallucinations and incorrect responses in GUI comprehension.To address these issues, we introduce VGA, a fine-tuned model designed for comprehensive GUI understanding. Our model aims to enhance the interpretation of visual data of GUI and reduce hallucinations. We first construct a Vision Question Answering (VQA) dataset of 63.8k high-quality examples with our propose Referent Method, which ensures the model's responses are highly depend on visual content within the image. We then design a two-stage fine-tuning method called Foundation and Advanced Comprehension (FAC) to enhance both the model's ability to extract information from image content and alignment with human intent. Experiments show that our approach enhances the model's ability to extract information from images and achieves state-of-the-art results in GUI understanding tasks. Our dataset and fine-tuning script will be released soon.

Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning

Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old classes. However, limited storage only allows storing a few representative videos. So we propose SNRO, which slightly shifts the features of new classes to remember old classes. Specifically, SNRO contains Examples Sparse(ES) and Early Break(EB). ES decimates at a lower sample rate to build memory sets and uses interpolation to align those sparse frames in the future. By this, SNRO stores more examples under the same memory consumption and forces the model to focus on low-semantic features which are harder to be forgotten. EB terminates the training at a small epoch, preventing the model from overstretching into the high-semantic space of the current task. Experiments on UCF101, HMDB51, and UESTC-MMEA-CL datasets show that SNRO performs better than other approaches while consuming the same memory consumption.

BAAF: A Benchmark Attention Adaptive Framework for Medical Ultrasound Image Segmentation Tasks

The AI-based assisted diagnosis programs have been widely investigated on medical ultrasound images. Complex scenario of ultrasound image, in which the coupled interference of internal and external factors is severe, brings a unique challenge for localize the object region automatically and precisely in ultrasound images. In this study, we seek to propose a more general and robust Benchmark Attention Adaptive Framework (BAAF) to assist doctors segment or diagnose lesions and tissues in ultrasound images more quickly and accurately. Different from existing attention schemes, the BAAF consists of a parallel hybrid attention module (PHAM) and an adaptive calibration mechanism (ACM). Specifically, BAAF first coarsely calibrates the input features from the channel and spatial dimensions, and then adaptively selects more robust lesion or tissue characterizations from the coarse-calibrated feature maps. The design of BAAF further optimizes the "what" and "where" focus and selection problems in CNNs and seeks to improve the segmentation accuracy of lesions or tissues in medical ultrasound images. The method is evaluated on four medical ultrasound segmentation tasks, and the adequate experimental results demonstrate the remarkable performance improvement over existing state-of-the-art methods. In addition, the comparison with existing attention mechanisms also demonstrates the superiority of BAAF. This work provides the possibility for automated medical ultrasound assisted diagnosis and reduces reliance on human accuracy and precision.

Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning

With the rapid development of wearable cameras, a massive collection of egocentric video for first-person visual perception becomes available. Using egocentric videos to predict first-person activity faces many challenges, including limited field of view, occlusions, and unstable motions. Observing that sensor data from wearable devices facilitates human activity recognition, multi-modal activity recognition is attracting increasing attention. However, the deficiency of related dataset hinders the development of multi-modal deep learning for egocentric activity recognition. Nowadays, deep learning in real world has led to a focus on continual learning that often suffers from catastrophic forgetting. But the catastrophic forgetting problem for egocentric activity recognition, especially in the context of multiple modalities, remains unexplored due to unavailability of dataset. In order to assist this research, we present a multi-modal egocentric activity dataset for continual learning named UESTC-MMEA-CL, which is collected by self-developed glasses integrating a first-person camera and wearable sensors. It contains synchronized data of videos, accelerometers, and gyroscopes, for 32 types of daily activities, performed by 10 participants. Its class types and scale are compared with other publicly available datasets. The statistical analysis of the sensor data is given to show the auxiliary effects for different behaviors. And results of egocentric activity recognition are reported when using separately, and jointly, three modalities: RGB, acceleration, and gyroscope, on a base network architecture. To explore the catastrophic forgetting in continual learning tasks, four baseline methods are extensively evaluated with different multi-modal combinations. We hope the UESTC-MMEA-CL can promote future studies on continual learning for first-person activity recognition in wearable applications.

ESKNet-An enhanced adaptive selection kernel convolution for breast tumors segmentation

Breast cancer is one of the common cancers that endanger the health of women globally. Accurate target lesion segmentation is essential for early clinical intervention and postoperative follow-up. Recently, many convolutional neural networks (CNNs) have been proposed to segment breast tumors from ultrasound images. However, the complex ultrasound pattern and the variable tumor shape and size bring challenges to the accurate segmentation of the breast lesion. Motivated by the selective kernel convolution, we introduce an enhanced selective kernel convolution for breast tumor segmentation, which integrates multiple feature map region representations and adaptively recalibrates the weights of these feature map regions from the channel and spatial dimensions. This region recalibration strategy enables the network to focus more on high-contributing region features and mitigate the perturbation of less useful regions. Finally, the enhanced selective kernel convolution is integrated into U-net with deep supervision constraints to adaptively capture the robust representation of breast tumors. Extensive experiments with twelve state-of-the-art deep learning segmentation methods on three public breast ultrasound datasets demonstrate that our method has a more competitive segmentation performance in breast ultrasound images.

NU-net: An Unpretentious Nested U-net for Breast Tumor Segmentation

Breast tumor segmentation is one of the key steps that helps us characterize and localize tumor regions. However, variable tumor morphology, blurred boundary, and similar intensity distributions bring challenges for accurate segmentation of breast tumors. Recently, many U-net variants have been proposed and widely used for breast tumors segmentation. However, these architectures suffer from two limitations: (1) Ignoring the characterize ability of the benchmark networks, and (2) Introducing extra complex operations increases the difficulty of understanding and reproducing the network. To alleviate these challenges, this paper proposes a simple yet powerful nested U-net (NU-net) for accurate segmentation of breast tumors. The key idea is to utilize U-Nets with different depths and shared weights to achieve robust characterization of breast tumors. NU-net mainly has the following advantages: (1) Improving network adaptability and robustness to breast tumors with different scales, (2) This method is easy to reproduce and execute, and (3) The extra operations increase network parameters without significantly increasing computational cost. Extensive experimental results with twelve state-of-the-art segmentation methods on three public breast ultrasound datasets demonstrate that NU-net has more competitive segmentation performance on breast tumors. Furthermore, the robustness of NU-net is further illustrated on the segmentation of renal ultrasound images. The source code is publicly available on https://github.com/CGPzy/NU-net.

BAGNet: Bidirectional Aware Guidance Network for Malignant Breast lesions Segmentation

Breast lesions segmentation is an important step of computer-aided diagnosis system, and it has attracted much attention. However, accurate segmentation of malignant breast lesions is a challenging task due to the effects of heterogeneous structure and similar intensity distributions. In this paper, a novel bidirectional aware guidance network (BAGNet) is proposed to segment the malignant lesion from breast ultrasound images. Specifically, the bidirectional aware guidance network is used to capture the context between global (low-level) and local (high-level) features from the input coarse saliency map. The introduction of the global feature map can reduce the interference of surrounding tissue (background) on the lesion regions. To evaluate the segmentation performance of the network, we compared with several state-of-the-art medical image segmentation methods on the public breast ultrasound dataset using six commonly used evaluation metrics. Extensive experimental results indicate that our method achieves the most competitive segmentation results on malignant breast ultrasound images.