Segmentation is a fundamental problem in surgical scene analysis using artificial intelligence. However, the inherent data scarcity in this domain makes it challenging to adapt traditional segmentation techniques for this task. To tackle this issue, current research employs pretrained models and finetunes them on the given data. Even so, these require training deep networks with millions of parameters every time new data becomes available. A recently published foundation model, Segment-Anything (SAM), generalizes well to a large variety of natural images, hence tackling this challenge to a reasonable extent. However, SAM does not generalize well to the medical domain as is without utilizing a large amount of compute resources for fine-tuning and using task-specific prompts. Moreover, these prompts are in the form of bounding-boxes or foreground/background points that need to be annotated explicitly for every image, making this solution increasingly tedious with higher data size. In this work, we propose AdaptiveSAM - an adaptive modification of SAM that can adjust to new datasets quickly and efficiently, while enabling text-prompted segmentation. For finetuning AdaptiveSAM, we propose an approach called bias-tuning that requires a significantly smaller number of trainable parameters than SAM (less than 2\%). At the same time, AdaptiveSAM requires negligible expert intervention since it uses free-form text as prompt and can segment the object of interest with just the label name as prompt. Our experiments show that AdaptiveSAM outperforms current state-of-the-art methods on various medical imaging datasets including surgery, ultrasound and X-ray. Code is available at https://github.com/JayParanjape/biastuning
Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics results in high uncertainty around the objects' boundaries and numerous false positives. We propose a paradigm change by shifting from a per-pixel classification to a mask classification. Our mask-based method, Mask2Anomaly, demonstrates the feasibility of integrating an anomaly detection method in a mask-classification architecture. Mask2Anomaly includes several technical novelties that are designed to improve the detection of anomalies in masks: i) a global masked attention module to focus individually on the foreground and background regions; ii) a mask contrastive learning that maximizes the margin between an anomaly and known classes; and iii) a mask refinement solution to reduce false positives. Mask2Anomaly achieves new state-of-the-art results across a range of benchmarks, both in the per-pixel and component-level evaluations. In particular, Mask2Anomaly reduces the average false positives rate by 60% wrt the previous state-of-the-art. Github page: https://github.com/shyam671/Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation.
Domain-generalized urban-scene semantic segmentation (USSS) aims to learn generalized semantic predictions across diverse urban-scene styles. Unlike domain gap challenges, USSS is unique in that the semantic categories are often similar in different urban scenes, while the styles can vary significantly due to changes in urban landscapes, weather conditions, lighting, and other factors. Existing approaches typically rely on convolutional neural networks (CNNs) to learn the content of urban scenes. In this paper, we propose a Content-enhanced Mask TransFormer (CMFormer) for domain-generalized USSS. The main idea is to enhance the focus of the fundamental component, the mask attention mechanism, in Transformer segmentation models on content information. To achieve this, we introduce a novel content-enhanced mask attention mechanism. It learns mask queries from both the image feature and its down-sampled counterpart, as lower-resolution image features usually contain more robust content information and are less sensitive to style variations. These features are fused into a Transformer decoder and integrated into a multi-resolution content-enhanced mask attention learning scheme. Extensive experiments conducted on various domain-generalized urban-scene segmentation datasets demonstrate that the proposed CMFormer significantly outperforms existing CNN-based methods for domain-generalized semantic segmentation, achieving improvements of up to 14.00\% in terms of mIoU (mean intersection over union). The source code is publicly available at \url{https://github.com/BiQiWHU/CMFormer}.
Accurate static structure reconstruction and segmentation of non-stationary objects is of vital importance for autonomous navigation applications. These applications assume a LiDAR scan to consist of only static structures. In the real world however, LiDAR scans consist of non-stationary dynamic structures - moving and movable objects. Current solutions use segmentation information to isolate and remove moving structures from LiDAR scan. This strategy fails in several important use-cases where segmentation information is not available. In such scenarios, moving objects and objects with high uncertainty in their motion i.e. movable objects, may escape detection. This violates the above assumption. We present MOVES, a novel GAN based adversarial model that segments out moving as well as movable objects in the absence of segmentation information. We achieve this by accurately transforming a dynamic LiDAR scan to its corresponding static scan. This is obtained by replacing dynamic objects and corresponding occlusions with static structures which were occluded by dynamic objects. We leverage corresponding static-dynamic LiDAR pairs.
Scene parsing is a great challenge for real-time semantic segmentation. Although traditional semantic segmentation networks have made remarkable leap-forwards in semantic accuracy, the performance of inference speed is unsatisfactory. Meanwhile, this progress is achieved with fairly large networks and powerful computational resources. However, it is difficult to run extremely large models on edge computing devices with limited computing power, which poses a huge challenge to the real-time semantic segmentation tasks. In this paper, we present the Cross-CBAM network, a novel lightweight network for real-time semantic segmentation. Specifically, a Squeeze-and-Excitation Atrous Spatial Pyramid Pooling Module(SE-ASPP) is proposed to get variable field-of-view and multiscale information. And we propose a Cross Convolutional Block Attention Module(CCBAM), in which a cross-multiply operation is employed in the CCBAM module to make high-level semantic information guide low-level detail information. Different from previous work, these works use attention to focus on the desired information in the backbone. CCBAM uses cross-attention for feature fusion in the FPN structure. Extensive experiments on the Cityscapes dataset and Camvid dataset demonstrate the effectiveness of the proposed Cross-CBAM model by achieving a promising trade-off between segmentation accuracy and inference speed. On the Cityscapes test set, we achieve 73.4% mIoU with a speed of 240.9FPS and 77.2% mIoU with a speed of 88.6FPS on NVIDIA GTX 1080Ti.
Video-grounded dialogue understanding is a challenging problem that requires machine to perceive, parse and reason over situated semantics extracted from weakly aligned video and dialogues. Most existing benchmarks treat both modalities the same as a frame-independent visual understanding task, while neglecting the intrinsic attributes in multimodal dialogues, such as scene and topic transitions. In this paper, we present Video-grounded Scene&Topic AwaRe dialogue (VSTAR) dataset, a large scale video-grounded dialogue understanding dataset based on 395 TV series. Based on VSTAR, we propose two benchmarks for video-grounded dialogue understanding: scene segmentation and topic segmentation, and one benchmark for video-grounded dialogue generation. Comprehensive experiments are performed on these benchmarks to demonstrate the importance of multimodal information and segments in video-grounded dialogue understanding and generation.
We present SSS3D, a fast multi-objective NAS framework designed to find computationally efficient 3D semantic scene segmentation networks. It uses RandLA-Net, an off-the-shelf point-based network, as a super-network to enable weight sharing and reduce search time by 99.67% for single-stage searches. SSS3D has a complex search space composed of sampling and architectural parameters that can form 2.88 * 10^17 possible networks. To further reduce search time, SSS3D splits the complete search space and introduces a two-stage search that finds optimal subnetworks in 54% of the time required by single-stage searches.
Advances in GPT-based large language models (LLMs) are revolutionizing natural language processing, exponentially increasing its use across various domains. Incorporating uni-directional attention, these autoregressive LLMs can generate long and coherent paragraphs. However, for visual question answering (VQA) tasks that require both vision and language processing, models with bi-directional attention or models employing fusion techniques are often employed to capture the context of multiple modalities all at once. As GPT does not natively process vision tokens, to exploit the advancements in GPT models for VQA in robotic surgery, we design an end-to-end trainable Language-Vision GPT (LV-GPT) model that expands the GPT2 model to include vision input (image). The proposed LV-GPT incorporates a feature extractor (vision tokenizer) and vision token embedding (token type and pose). Given the limitations of unidirectional attention in GPT models and their ability to generate coherent long paragraphs, we carefully sequence the word tokens before vision tokens, mimicking the human thought process of understanding the question to infer an answer from an image. Quantitatively, we prove that the LV-GPT model outperforms other state-of-the-art VQA models on two publically available surgical-VQA datasets (based on endoscopic vision challenge robotic scene segmentation 2018 and CholecTriplet2021) and on our newly annotated dataset (based on the holistic surgical scene dataset). We further annotate all three datasets to include question-type annotations to allow sub-type analysis. Furthermore, we extensively study and present the effects of token sequencing, token type and pose embedding for vision tokens in the LV-GPT model.
Understanding semantic scene segmentation of urban scenes captured from the Unmanned Aerial Vehicles (UAV) perspective plays a vital role in building a perception model for UAV. With the limitations of large-scale densely labeled data, semantic scene segmentation for UAV views requires a broad understanding of an object from both its top and side views. Adapting from well-annotated autonomous driving data to unlabeled UAV data is challenging due to the cross-view differences between the two data types. Our work proposes a novel Cross-View Adaptation (CROVIA) approach to effectively adapt the knowledge learned from on-road vehicle views to UAV views. First, a novel geometry-based constraint to cross-view adaptation is introduced based on the geometry correlation between views. Second, cross-view correlations from image space are effectively transferred to segmentation space without any requirement of paired on-road and UAV view data via a new Geometry-Constraint Cross-View (GeiCo) loss. Third, the multi-modal bijective networks are introduced to enforce the global structural modeling across views. Experimental results on new cross-view adaptation benchmarks introduced in this work, i.e., SYNTHIA to UAVID and GTA5 to UAVID, show the State-of-the-Art (SOTA) performance of our approach over prior adaptation methods
Although Domain Adaptation in Semantic Scene Segmentation has shown impressive improvement in recent years, the fairness concerns in the domain adaptation have yet to be well defined and addressed. In addition, fairness is one of the most critical aspects when deploying the segmentation models into human-related real-world applications, e.g., autonomous driving, as any unfair predictions could influence human safety. In this paper, we propose a novel Fairness Domain Adaptation (FREDOM) approach to semantic scene segmentation. In particular, from the proposed formulated fairness objective, a new adaptation framework will be introduced based on the fair treatment of class distributions. Moreover, to generally model the context of structural dependency, a new conditional structural constraint is introduced to impose the consistency of predicted segmentation. Thanks to the proposed Conditional Structure Network, the self-attention mechanism has sufficiently modeled the structural information of segmentation. Through the ablation studies, the proposed method has shown the performance improvement of the segmentation models and promoted fairness in the model predictions. The experimental results on the two standard benchmarks, i.e., SYNTHIA $\to$ Cityscapes and GTA5 $\to$ Cityscapes, have shown that our method achieved State-of-the-Art (SOTA) performance.
Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to directly apply Transformers on point clouds due to their quadratic cost in the number of points. In this paper, we present a Self-Positioning point-based Transformer (SPoTr), which is designed to capture both local and global shape contexts with reduced complexity. Specifically, this architecture consists of local self-attention and self-positioning point-based global cross-attention. The self-positioning points, adaptively located based on the input shape, consider both spatial and semantic information with disentangled attention to improve expressive power. With the self-positioning points, we propose a novel global cross-attention mechanism for point clouds, which improves the scalability of global self-attention by allowing the attention module to compute attention weights with only a small set of self-positioning points. Experiments show the effectiveness of SPoTr on three point cloud tasks such as shape classification, part segmentation, and scene segmentation. In particular, our proposed model achieves an accuracy gain of 2.6% over the previous best models on shape classification with ScanObjectNN. We also provide qualitative analyses to demonstrate the interpretability of self-positioning points. The code of SPoTr is available at https://github.com/mlvlab/SPoTr.
Scene segmentation is widely used in the field of autonomous driving for environment perception, and semantic scene segmentation (3S) has received a great deal of attention due to the richness of the semantic information it contains. It aims to assign labels to pixels in an image, thus enabling automatic image labeling. Current approaches are mainly based on convolutional neural networks (CNN), but they rely on a large number of labels. Therefore, how to use a small size of labeled data to achieve semantic segmentation becomes more and more important. In this paper, we propose a domain adaptation (DA) framework based on optimal transport (OT) and attention mechanism to address this issue. Concretely, first we generate the output space via CNN due to its superiority of feature representation. Second, we utilize OT to achieve a more robust alignment of source and target domains in output space, where the OT plan defines a well attention mechanism to improve the adaptation of the model. In particular, with OT, the number of network parameters has been reduced and the network has been better interpretable. Third, to better describe the multi-scale property of features, we construct a multi-scale segmentation network to perform domain adaptation. Finally, in order to verify the performance of our proposed method, we conduct experimental comparison with three benchmark and four SOTA methods on three scene datasets, and the mean intersection-over-union (mIOU) has been significant improved, and visualization results under multiple domain adaptation scenarios also show that our proposed method has better performance than compared semantic segmentation methods.
Movie highlights stand out of the screenplay for efficient browsing and play a crucial role on social media platforms. Based on existing efforts, this work has two observations: (1) For different annotators, labeling highlight has uncertainty, which leads to inaccurate and time-consuming annotations. (2) Besides previous supervised or unsupervised settings, some existing video corpora can be useful, e.g., trailers, but they are often noisy and incomplete to cover the full highlights. In this work, we study a more practical and promising setting, i.e., reformulating highlight detection as "learning with noisy labels". This setting does not require time-consuming manual annotations and can fully utilize existing abundant video corpora. First, based on movie trailers, we leverage scene segmentation to obtain complete shots, which are regarded as noisy labels. Then, we propose a Collaborative noisy Label Cleaner (CLC) framework to learn from noisy highlight moments. CLC consists of two modules: augmented cross-propagation (ACP) and multi-modality cleaning (MMC). The former aims to exploit the closely related audio-visual signals and fuse them to learn unified multi-modal representations. The latter aims to achieve cleaner highlight labels by observing the changes in losses among different modalities. To verify the effectiveness of CLC, we further collect a large-scale highlight dataset named MovieLights. Comprehensive experiments on MovieLights and YouTube Highlights datasets demonstrate the effectiveness of our approach. Code has been made available at: https://github.com/TencentYoutuResearch/HighlightDetection-CLC
Robust semantic segmentation of intraoperative image data could pave the way for automatic surgical scene understanding and autonomous robotic surgery. Geometric domain shifts, however, although common in real-world open surgeries due to variations in surgical procedures or situs occlusions, remain a topic largely unaddressed in the field. To address this gap in the literature, we (1) present the first analysis of state-of-the-art (SOA) semantic segmentation networks in the presence of geometric out-of-distribution (OOD) data, and (2) address generalizability with a dedicated augmentation technique termed "Organ Transplantation" that we adapted from the general computer vision community. According to a comprehensive validation on six different OOD data sets comprising 600 RGB and hyperspectral imaging (HSI) cubes from 33 pigs semantically annotated with 19 classes, we demonstrate a large performance drop of SOA organ segmentation networks applied to geometric OOD data. Surprisingly, this holds true not only for conventional RGB data (drop of Dice similarity coefficient (DSC) by 46 %) but also for HSI data (drop by 45 %), despite the latter's rich information content per pixel. Using our augmentation scheme improves on the SOA DSC by up to 67 % (RGB) and 90 % (HSI) and renders performance on par with in-distribution performance on real OOD test data. The simplicity and effectiveness of our augmentation scheme makes it a valuable network-independent tool for addressing geometric domain shifts in semantic scene segmentation of intraoperative data. Our code and pre-trained models are available at https://github.com/IMSY-DKFZ/htc.
Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided at run-time in the form of text prompts, as opposed to a fixed set of classes defined at training time. In this work, we present a zero-shot volumetric open-vocabulary semantic scene segmentation method. Our method builds on the insight that we can fuse image features from a vision-language model into a neural implicit representation. We show that the resulting feature field can be segmented into different classes by assigning points to natural language text prompts. The implicit volumetric representation enables us to segment the scene both in 3D and 2D by rendering feature maps from any given viewpoint of the scene. We show that our method works on noisy real-world data and can run in real-time on live sensor data dynamically adjusting to text prompts. We also present quantitative comparisons on the ScanNet dataset.
The mainstream CNN-based remote sensing (RS) image semantic segmentation approaches typically rely on massive labeled training data. Such a paradigm struggles with the problem of RS multi-view scene segmentation with limited labeled views due to the lack of considering 3D information within the scene. In this paper, we propose ''Implicit Ray-Transformer (IRT)'' based on Implicit Neural Representation (INR), for RS scene semantic segmentation with sparse labels (such as 4-6 labels per 100 images). We explore a new way of introducing multi-view 3D structure priors to the task for accurate and view-consistent semantic segmentation. The proposed method includes a two-stage learning process. In the first stage, we optimize a neural field to encode the color and 3D structure of the remote sensing scene based on multi-view images. In the second stage, we design a Ray Transformer to leverage the relations between the neural field 3D features and 2D texture features for learning better semantic representations. Different from previous methods that only consider 3D prior or 2D features, we incorporate additional 2D texture information and 3D prior by broadcasting CNN features to different point features along the sampled ray. To verify the effectiveness of the proposed method, we construct a challenging dataset containing six synthetic sub-datasets collected from the Carla platform and three real sub-datasets from Google Maps. Experiments show that the proposed method outperforms the CNN-based methods and the state-of-the-art INR-based segmentation methods in quantitative and qualitative metrics.
Manual labeling of gestures in robot-assisted surgery is labor intensive, prone to errors, and requires expertise or training. We propose a method for automated and explainable generation of gesture transcripts that leverages the abundance of data for image segmentation. Surgical context is detected using segmentation masks by examining the distances and intersections between the tools and objects. Next, context labels are translated into gesture transcripts using knowledge-based Finite State Machine (FSM) and data-driven Long Short Term Memory (LSTM) models. We evaluate the performance of each stage of our method by comparing the results with the ground truth segmentation masks, the consensus context labels, and the gesture labels in the JIGSAWS dataset. Our results show that our segmentation models achieve state-of-the-art performance in recognizing needle and thread in Suturing and we can automatically detect important surgical states with high agreement with crowd-sourced labels (e.g., contact between graspers and objects in Suturing). We also find that the FSM models are more robust to poor segmentation and labeling performance than LSTMs. Our proposed method can significantly shorten the gesture labeling process (~2.8 times).
Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods heavily rely on the ability to score the difficulty of data samples, an optimal scoring function is still under exploration. Methodology: Distillation is a knowledge transfer approach where a teacher network guides a student network by feeding a sequence of random samples. We argue that guiding student networks with an efficient curriculum strategy can improve model generalization and robustness. For this purpose, we design an uncertainty-based paced curriculum learning in self distillation for medical image segmentation. We fuse the prediction uncertainty and annotation boundary uncertainty to develop a novel paced-curriculum distillation (PCD). We utilize the teacher model to obtain prediction uncertainty and spatially varying label smoothing with Gaussian kernel to generate segmentation boundary uncertainty from the annotation. We also investigate the robustness of our method by applying various types and severity of image perturbation and corruption. Results: The proposed technique is validated on two medical datasets of breast ultrasound image segmentation and robotassisted surgical scene segmentation and achieved significantly better performance in terms of segmentation and robustness. Conclusion: P-CD improves the performance and obtains better generalization and robustness over the dataset shift. While curriculum learning requires extensive tuning of hyper-parameters for pacing function, the level of performance improvement suppresses this limitation.
The ability to distinguish between different movie scenes is critical for understanding the storyline of a movie. However, accurately detecting movie scenes is often challenging as it requires the ability to reason over very long movie segments. This is in contrast to most existing video recognition models, which are typically designed for short-range video analysis. This work proposes a State-Space Transformer model that can efficiently capture dependencies in long movie videos for accurate movie scene detection. Our model, dubbed TranS4mer, is built using a novel S4A building block, which combines the strengths of structured state-space sequence (S4) and self-attention (A) layers. Given a sequence of frames divided into movie shots (uninterrupted periods where the camera position does not change), the S4A block first applies self-attention to capture short-range intra-shot dependencies. Afterward, the state-space operation in the S4A block is used to aggregate long-range inter-shot cues. The final TranS4mer model, which can be trained end-to-end, is obtained by stacking the S4A blocks one after the other multiple times. Our proposed TranS4mer outperforms all prior methods in three movie scene detection datasets, including MovieNet, BBC, and OVSD, while also being $2\times$ faster and requiring $3\times$ less GPU memory than standard Transformer models. We will release our code and models.
In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this information can be used to perform segmentation or single-view depth estimation even though the networks were only trained for image recognition. We show that a similar phenomenon occurs when explicitly training transformers for semantic segmentation in a supervised manner for a set of categories: Once trained, they provide valuable information even about categories absent from the training set. This information can be used to segment objects from these never-seen-before classes in domains as varied as road obstacles, aircraft parked at a terminal, lunar rocks, and maritime hazards.