In this paper, we propose a novel text promptable surgical instrument segmentation approach to overcome challenges associated with diversity and differentiation of surgical instruments in minimally invasive surgeries. We redefine the task as text promptable, thereby enabling a more nuanced comprehension of surgical instruments and adaptability to new instrument types. Inspired by recent advancements in vision-language models, we leverage pretrained image and text encoders as our model backbone and design a text promptable mask decoder consisting of attention- and convolution-based prompting schemes for surgical instrument segmentation prediction. Our model leverages multiple text prompts for each surgical instrument through a new mixture of prompts mechanism, resulting in enhanced segmentation performance. Additionally, we introduce a hard instrument area reinforcement module to improve image feature comprehension and segmentation precision. Extensive experiments on EndoVis2017 and EndoVis2018 datasets demonstrate our model's superior performance and promising generalization capability. To our knowledge, this is the first implementation of a promptable approach to surgical instrument segmentation, offering significant potential for practical application in the field of robotic-assisted surgery.
Referring video object segmentation (RVOS) aims to segment the target instance referred by a given text expression in a video clip. The text expression normally contains sophisticated descriptions of the instance's appearance, actions, and relations with others. It is therefore rather difficult for an RVOS model to capture all these attributes correspondingly in the video; in fact, the model often favours more on the action- and relation-related visual attribute of the instance. This can end up with incomplete or even incorrect mask prediction of the target instance. In this paper, we tackle this problem by taking a subject-centric short text expression from the original long text expression. The short one retains only the appearance-related information of the target instance so that we can use it to focus the model's attention on the instance's appearance. We let the model make joint predictions using both long and short text expressions and introduce a long-short predictions intersection loss to align the joint predictions. Besides the improvement on the linguistic part, we also introduce a forward-backward visual consistency loss, which utilizes optical flows to warp visual features between the annotated frames and their temporal neighbors for consistency. We build our method on top of two state of the art transformer-based pipelines for end-to-end training. Extensive experiments on A2D-Sentences and JHMDB-Sentences datasets show impressive improvements of our method.
Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to build a scene graph. This task is particularly challenging for two reasons. First, it suffers from a long-tail problem in its relation categories, making naive biased methods more inclined to high-frequency relations. Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations. Second, a subject-object pair can have two or more semantically overlapping relations. While existing methods favor one over the other, our proposed HiLo framework lets different network branches specialize on low and high frequency relations, enforce their consistency and fuse the results. To the best of our knowledge we are the first to propose an explicitly unbiased PSG method. In extensive experiments we show that our HiLo framework achieves state-of-the-art results on the PSG task. We also apply our method to the Scene Graph Generation task that predicts boxes instead of masks and see improvements over all baseline methods.
Domain shift across crowd data severely hinders crowd counting models to generalize to unseen scenarios. Although domain adaptive crowd counting approaches close this gap to a certain extent, they are still dependent on the target domain data to adapt (e.g. finetune) their models to the specific domain. In this paper, we aim to train a model based on a single source domain which can generalize well on any unseen domain. This falls into the realm of domain generalization that remains unexplored in crowd counting. We first introduce a dynamic sub-domain division scheme which divides the source domain into multiple sub-domains such that we can initiate a meta-learning framework for domain generalization. The sub-domain division is dynamically refined during the meta-learning. Next, in order to disentangle domain-invariant information from domain-specific information in image features, we design the domain-invariant and -specific crowd memory modules to re-encode image features. Two types of losses, i.e. feature reconstruction and orthogonal losses, are devised to enable this disentanglement. Extensive experiments on several standard crowd counting benchmarks i.e. SHA, SHB, QNRF, and NWPU, show the strong generalizability of our method.
Wikidata is an open knowledge graph created, managed, and maintained collaboratively by a global community of volunteers. As it continues to grow, it faces substantial editor engagement challenges, including acquiring new editors to tackle an increasing workload and retaining existing editors. Experiences from other online communities and peer-production systems, including Wikipedia, suggest that recommending tasks to editors could help with both. Our aim with this paper is to elicit the user requirements for a Wikidata recommendations system. We conduct a mixed-methods study with a thematic analysis of in-depth interviews with 31 Wikidata editors and three Wikimedia managers, complemented by a quantitative analysis of edit records of 3,740 Wikidata editors. The insights gained from the study help us outline design requirements for the Wikidata recommender system. We conclude with a discussion of the implications of this work and directions for future work.
Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning. Since the discovery that original DARTS will inevitably converge to poor architectures, recent works alleviate this by either designing rule-based architecture selection techniques or incorporating complex regularization techniques, abandoning the simplicity of the original DARTS that selects architectures based on the largest parametric value, namely $\alpha$. Moreover, we find that all the previous attempts only rely on classification labels, hence learning only single modal information and limiting the representation power of the shared network. To this end, we propose to additionally inject semantic information by formulating a patch recovery approach. Specifically, we exploit the recent trending masked image modeling and do not abandon the guidance from the downstream tasks during the search phase. Our method surpasses all previous DARTS variants and achieves state-of-the-art results on CIFAR-10, CIFAR-100, and ImageNet without complex manual-designed strategies.
Video-based remote physiological measurement aims to estimate remote photoplethysmography (rPPG) signals from human face videos and then measure multiple vital signs (e.g. heart rate, respiration frequency) from rPPG signals. Recent approaches achieve it by training deep neural networks, which normally require abundant face videos and synchronously recorded photoplethysmography (PPG) signals for supervision. However, the collection of these annotated corpora is uneasy in practice. In this paper, we introduce a novel frequency-inspired self-supervised framework that learns to estimate rPPG signals from face videos without the need of ground truth PPG signals. Given a video sample, we first augment it into multiple positive/negative samples which contain similar/dissimilar signal frequencies to the original one. Specifically, positive samples are generated using spatial augmentation. Negative samples are generated via a learnable frequency augmentation module, which performs non-linear signal frequency transformation on the input without excessively changing its visual appearance. Next, we introduce a local rPPG expert aggregation module to estimate rPPG signals from augmented samples. It encodes complementary pulsation information from different face regions and aggregate them into one rPPG prediction. Finally, we propose a series of frequency-inspired losses, i.e. frequency contrastive loss, frequency ratio consistency loss, and cross-video frequency agreement loss, for the optimization of estimated rPPG signals from multiple augmented video samples and across temporally neighboring video samples. We conduct rPPG-based heart rate, heart rate variability and respiration frequency estimation on four standard benchmarks. The experimental results demonstrate that our method improves the state of the art by a large margin.
In computer vision there has been significant research interest in assessing potential demographic bias in deep learning models. One of the main causes of such bias is imbalance in the training data. In medical imaging, where the potential impact of bias is arguably much greater, there has been less interest. In medical imaging pipelines, segmentation of structures of interest plays an important role in estimating clinical biomarkers that are subsequently used to inform patient management. Convolutional neural networks (CNNs) are starting to be used to automate this process. We present the first systematic study of the impact of training set imbalance on race and sex bias in CNN-based segmentation. We focus on segmentation of the structures of the heart from short axis cine cardiac magnetic resonance images, and train multiple CNN segmentation models with different levels of race/sex imbalance. We find no significant bias in the sex experiment but significant bias in two separate race experiments, highlighting the need to consider adequate representation of different demographic groups in health datasets.
Perspective distortions and crowd variations make crowd counting a challenging task in computer vision. To tackle it, many previous works have used multi-scale architecture in deep neural networks (DNNs). Multi-scale branches can be either directly merged (e.g. by concatenation) or merged through the guidance of proxies (e.g. attentions) in the DNNs. Despite their prevalence, these combination methods are not sophisticated enough to deal with the per-pixel performance discrepancy over multi-scale density maps. In this work, we redesign the multi-scale neural network by introducing a hierarchical mixture of density experts, which hierarchically merges multi-scale density maps for crowd counting. Within the hierarchical structure, an expert competition and collaboration scheme is presented to encourage contributions from all scales; pixel-wise soft gating nets are introduced to provide pixel-wise soft weights for scale combinations in different hierarchies. The network is optimized using both the crowd density map and the local counting map, where the latter is obtained by local integration on the former. Optimizing both can be problematic because of their potential conflicts. We introduce a new relative local counting loss based on relative count differences among hard-predicted local regions in an image, which proves to be complementary to the conventional absolute error loss on the density map. Experiments show that our method achieves the state-of-the-art performance on five public datasets, i.e. ShanghaiTech, UCF_CC_50, JHU-CROWD++, NWPU-Crowd and Trancos.
The target of space-time video super-resolution (STVSR) is to increase both the frame rate (also referred to as the temporal resolution) and the spatial resolution of a given video. Recent approaches solve STVSR with end-to-end deep neural networks. A popular solution is to first increase the frame rate of the video; then perform feature refinement among different frame features; and last increase the spatial resolutions of these features. The temporal correlation among features of different frames is carefully exploited in this process. The spatial correlation among features of different (spatial) resolutions, despite being also very important, is however not emphasized. In this paper, we propose a spatial-temporal feature interaction network to enhance STVSR by exploiting both spatial and temporal correlations among features of different frames and spatial resolutions. Specifically, the spatial-temporal frame interpolation module is introduced to interpolate low- and high-resolution intermediate frame features simultaneously and interactively. The spatial-temporal local and global refinement modules are respectively deployed afterwards to exploit the spatial-temporal correlation among different features for their refinement. Finally, a novel motion consistency loss is employed to enhance the motion continuity among reconstructed frames. We conduct experiments on three standard benchmarks, Vid4, Vimeo-90K and Adobe240, and the results demonstrate that our method improves the state of the art methods by a considerable margin. Our codes will be available at https://github.com/yuezijie/STINet-Space-time-Video-Super-resolution.