A serious issue that harms the performance of zero-shot visual recognition is named objective misalignment, i.e., the learning objective prioritizes improving the recognition accuracy of seen classes rather than unseen classes, while the latter is the true target to pursue. This issue becomes more significant in zero-shot image segmentation because the stronger (i.e., pixel-level) supervision brings a larger gap between seen and unseen classes. To mitigate it, we propose a novel architecture named AlignZeg, which embodies a comprehensive improvement of the segmentation pipeline, including proposal extraction, classification, and correction, to better fit the goal of zero-shot segmentation. (1) Mutually-Refined Proposal Extraction. AlignZeg harnesses a mutual interaction between mask queries and visual features, facilitating detailed class-agnostic mask proposal extraction. (2) Generalization-Enhanced Proposal Classification. AlignZeg introduces synthetic data and incorporates multiple background prototypes to allocate a more generalizable feature space. (3) Predictive Bias Correction. During the inference stage, AlignZeg uses a class indicator to find potential unseen class proposals followed by a prediction postprocess to correct the prediction bias. Experiments demonstrate that AlignZeg markedly enhances zero-shot semantic segmentation, as shown by an average 3.8% increase in hIoU, primarily attributed to a 7.1% improvement in identifying unseen classes, and we further validate that the improvement comes from alleviating the objective misalignment issue.
We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot segmentation models. Contrasted to prior 3D scene segmentation approaches that heavily rely on video object tracking, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses. By eliminating the assumption of continuous view changes in training images, Gaga demonstrates robustness to variations in camera poses, particularly beneficial for sparsely sampled images, ensuring precise mask label consistency. Furthermore, Gaga accommodates 2D segmentation masks from diverse sources and demonstrates robust performance with different open-world zero-shot segmentation models, enhancing its versatility. Extensive qualitative and quantitative evaluations demonstrate that Gaga performs favorably against state-of-the-art methods, emphasizing its potential for real-world applications such as scene understanding and manipulation.
The Segment Anything Model (SAM) and CLIP are remarkable vision foundation models (VFMs). SAM, a prompt driven segmentation model, excels in segmentation tasks across diverse domains, while CLIP is renowned for its zero shot recognition capabilities. However, their unified potential has not yet been explored in medical image segmentation. To adapt SAM to medical imaging, existing methods primarily rely on tuning strategies that require extensive data or prior prompts tailored to the specific task, making it particularly challenging when only a limited number of data samples are available. This work presents an in depth exploration of integrating SAM and CLIP into a unified framework for medical image segmentation. Specifically, we propose a simple unified framework, SaLIP, for organ segmentation. Initially, SAM is used for part based segmentation within the image, followed by CLIP to retrieve the mask corresponding to the region of interest (ROI) from the pool of SAM generated masks. Finally, SAM is prompted by the retrieved ROI to segment a specific organ. Thus, SaLIP is training and fine tuning free and does not rely on domain expertise or labeled data for prompt engineering. Our method shows substantial enhancements in zero shot segmentation, showcasing notable improvements in DICE scores across diverse segmentation tasks like brain (63.46%), lung (50.11%), and fetal head (30.82%), when compared to un prompted SAM. Code and text prompts will be available online.
The recent success of CLIP has demonstrated promising results in zero-shot semantic segmentation by transferring muiltimodal knowledge to pixel-level classification. However, leveraging pre-trained CLIP knowledge to closely align text embeddings with pixel embeddings still has limitations in existing approaches. To address this issue, we propose OTSeg, a novel multimodal attention mechanism aimed at enhancing the potential of multiple text prompts for matching associated pixel embeddings. We first propose Multi-Prompts Sinkhorn (MPS) based on the Optimal Transport (OT) algorithm, which leads multiple text prompts to selectively focus on various semantic features within image pixels. Moreover, inspired by the success of Sinkformers in unimodal settings, we introduce the extension of MPS, called Multi-Prompts Sinkhorn Attention (MPSA), which effectively replaces cross-attention mechanisms within Transformer framework in multimodal settings. Through extensive experiments, we demonstrate that OTSeg achieves state-of-the-art (SOTA) performance with significant gains on Zero-Shot Semantic Segmentation (ZS3) tasks across three benchmark datasets.
Rapid advancements in continual segmentation have yet to bridge the gap of scaling to large continually expanding vocabularies under compute-constrained scenarios. We discover that traditional continual training leads to catastrophic forgetting under compute constraints, unable to outperform zero-shot segmentation methods. We introduce a novel strategy for semantic and panoptic segmentation with zero forgetting, capable of adapting to continually growing vocabularies without the need for retraining or large memory costs. Our training-free approach, kNN-CLIP, leverages a database of instance embeddings to enable open-vocabulary segmentation approaches to continually expand their vocabulary on any given domain with a single-pass through data, while only storing embeddings minimizing both compute and memory costs. This method achieves state-of-the-art mIoU performance across large-vocabulary semantic and panoptic segmentation datasets. We hope kNN-CLIP represents a step forward in enabling more efficient and adaptable continual segmentation, paving the way for advances in real-world large-vocabulary continual segmentation methods.
The Segment Anything Model (SAM) is a deep neural network foundational model designed to perform instance segmentation which has gained significant popularity given its zero-shot segmentation ability. SAM operates by generating masks based on various input prompts such as text, bounding boxes, points, or masks, introducing a novel methodology to overcome the constraints posed by dataset-specific scarcity. While SAM is trained on an extensive dataset, comprising ~11M images, it mostly consists of natural photographic images with only very limited images from other modalities. Whilst the rapid progress in visual infrared surveillance and X-ray security screening imaging technologies, driven forward by advances in deep learning, has significantly enhanced the ability to detect, classify and segment objects with high accuracy, it is not evident if the SAM zero-shot capabilities can be transferred to such modalities. This work assesses SAM capabilities in segmenting objects of interest in the X-ray/infrared modalities. Our approach reuses the pre-trained SAM with three different prompts: bounding box, centroid and random points. We present quantitative/qualitative results to showcase the performance on selected datasets. Our results show that SAM can segment objects in the X-ray modality when given a box prompt, but its performance varies for point prompts. Specifically, SAM performs poorly in segmenting slender objects and organic materials, such as plastic bottles. We find that infrared objects are also challenging to segment with point prompts given the low-contrast nature of this modality. This study shows that while SAM demonstrates outstanding zero-shot capabilities with box prompts, its performance ranges from moderate to poor for point prompts, indicating that special consideration on the cross-modal generalisation of SAM is needed when considering use on X-ray/infrared imagery.
The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness, prevailing methods within this paradigm encounter challenges, including overfitting on seen classes and small fragmentation in masks. To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information.Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Moreover, to circumvent noisy alignments from the vision part due to its redundant nature, we introduce route attention into self-attention for finding visual consensus, thereby enhancing semantic consistency within the same object. Equipped with a vision-language prompting strategy, our approach significantly boosts the generalization capacity of segmentation models for unseen classes. Experimental results underscore the effectiveness of our approach, showcasing mIoU gains of 4.5 on the PASCAL VOC 2012 and 3.6 on the COCO-Stuff 164k for unseen classes compared with the state-of-the-art methods.
Cross-modality image segmentation aims to segment the target modalities using a method designed in the source modality. Deep generative models can translate the target modality images into the source modality, thus enabling cross-modality segmentation. However, a vast body of existing cross-modality image translation methods relies on supervised learning. In this work, we aim to address the challenge of zero-shot learning-based image translation tasks (extreme scenarios in the target modality is unseen in the training phase). To leverage generative learning for zero-shot cross-modality image segmentation, we propose a novel unsupervised image translation method. The framework learns to translate the unseen source image to the target modality for image segmentation by leveraging the inherent statistical consistency between different modalities for diffusion guidance. Our framework captures identical cross-modality features in the statistical domain, offering diffusion guidance without relying on direct mappings between the source and target domains. This advantage allows our method to adapt to changing source domains without the need for retraining, making it highly practical when sufficient labeled source domain data is not available. The proposed framework is validated in zero-shot cross-modality image segmentation tasks through empirical comparisons with influential generative models, including adversarial-based and diffusion-based models.
The ability of a robot to pick an object, known as robot grasping, is crucial for several applications, such as assembly or sorting. In such tasks, selecting the right target to pick is as essential as inferring a correct configuration of the gripper. A common solution to this problem relies on semantic segmentation models, which often show poor generalization to unseen objects and require considerable time and massive data to be trained. To reduce the need for large datasets, some grasping pipelines exploit few-shot semantic segmentation models, which are capable of recognizing new classes given a few examples. However, this often comes at the cost of limited performance and fine-tuning is required to be effective in robot grasping scenarios. In this work, we propose to overcome all these limitations by combining the impressive generalization capability reached by foundation models with a high-performing few-shot classifier, working as a score function to select the segmentation that is closer to the support set. The proposed model is designed to be embedded in a grasp synthesis pipeline. The extensive experiments using one or five examples show that our novel approach overcomes existing performance limitations, improving the state of the art both in few-shot semantic segmentation on the Graspnet-1B (+10.5% mIoU) and Ocid-grasp (+1.6% AP) datasets, and real-world few-shot grasp synthesis (+21.7% grasp accuracy). The project page is available at: https://leobarcellona.github.io/showandgrasp.github.io/
Medical image segmentation of anatomical structures and pathology is crucial in modern clinical diagnosis, disease study, and treatment planning. To date, great progress has been made in deep learning-based segmentation techniques, but most methods still lack data efficiency, generalizability, and interactability. Consequently, the development of new, precise segmentation methods that demand fewer labeled datasets is of utmost importance in medical image analysis. Recently, the emergence of foundation models, such as CLIP and Segment-Anything-Model (SAM), with comprehensive cross-domain representation opened the door for interactive and universal image segmentation. However, exploration of these models for data-efficient medical image segmentation is still limited, but is highly necessary. In this paper, we propose a novel framework, called MedCLIP-SAM that combines CLIP and SAM models to generate segmentation of clinical scans using text prompts in both zero-shot and weakly supervised settings. To achieve this, we employed a new Decoupled Hard Negative Noise Contrastive Estimation (DHN-NCE) loss to fine-tune the BiomedCLIP model and the recent gScoreCAM to generate prompts to obtain segmentation masks from SAM in a zero-shot setting. Additionally, we explored the use of zero-shot segmentation labels in a weakly supervised paradigm to improve the segmentation quality further. By extensively testing three diverse segmentation tasks and medical image modalities (breast tumor ultrasound, brain tumor MRI, and lung X-ray), our proposed framework has demonstrated excellent accuracy.