Zero-shot Semantic Segmentation (ZSS) aims to segment categories that are not annotated during training. While fine-tuning vision-language models has achieved promising results, these models often overfit to seen categories due to the lack of supervision for unseen classes. As an alternative to fully supervised approaches, query-based segmentation has shown great latent in ZSS, as it enables object localization without relying on explicit labels. However, conventional Hungarian matching, a core component in query-based frameworks, needs full supervision and often misclassifies unseen categories as background in the setting of ZSS. To address this issue, we propose Split Matching (SM), a novel assignment strategy that decouples Hungarian matching into two components: one for seen classes in annotated regions and another for latent classes in unannotated regions (referred to as unseen candidates). Specifically, we partition the queries into seen and candidate groups, enabling each to be optimized independently according to its available supervision. To discover unseen candidates, we cluster CLIP dense features to generate pseudo masks and extract region-level embeddings using CLS tokens. Matching is then conducted separately for the two groups based on both class-level similarity and mask-level consistency. Additionally, we introduce a Multi-scale Feature Enhancement (MFE) module that refines decoder features through residual multi-scale aggregation, improving the model's ability to capture spatial details across resolutions. SM is the first to introduce decoupled Hungarian matching under the inductive ZSS setting, and achieves state-of-the-art performance on two standard benchmarks.
Existing zero-shot 3D point cloud segmentation methods often struggle with limited transferability from seen classes to unseen classes and from semantic to visual space. To alleviate this, we introduce 3D-PointZshotS, a geometry-aware zero-shot segmentation framework that enhances both feature generation and alignment using latent geometric prototypes (LGPs). Specifically, we integrate LGPs into a generator via a cross-attention mechanism, enriching semantic features with fine-grained geometric details. To further enhance stability and generalization, we introduce a self-consistency loss, which enforces feature robustness against point-wise perturbations. Additionally, we re-represent visual and semantic features in a shared space, bridging the semantic-visual gap and facilitating knowledge transfer to unseen classes. Experiments on three real-world datasets, namely ScanNet, SemanticKITTI, and S3DIS, demonstrate that our method achieves superior performance over four baselines in terms of harmonic mIoU. The code is available at \href{https://github.com/LexieYang/3D-PointZshotS}{Github}.
Generalized zero-shot semantic segmentation (GZS3) aims to achieve the human-level capability of segmenting not only seen classes but also novel class regions unseen in the training data through introducing the bridge of semantic representations, e.g., word vector. While effective, the way of utilizing one semantic representation to associate the corresponding class and to enable the knowledge transfer from seen to unseen classes is insufficient as well as incompatible with human cognition. Inspired by the observation that humans often use some `part' and `state' information to comprehend the seen objects and imagine unseen classes, we decouple each class into detailed descriptions, including object parts and states. Based on the decoupling formulation, we propose a Decoupled Vision-Language Matching (DeVLMatch) framework, composed of spatial-part (SPMatch) and channel-state (CSMatch) matching modules, for GZS3. In SPMatch, we comprehend objects with spatial part information from both visual and linguistic perspectives and perform graph matching to bridge the gap. In CSMatch, states of objects from the linguistic perspective are matched to compatible channel information from the visual perspective. By decoupling and matching objects across visual and linguistic comprehension, we can explicitly introspect the relationship between seen and unseen classes in fine-grained object part and state levels, thereby facilitating the knowledge transfer from seen to unseen classes in visual space. The proposed DeVLMatch framework surpasses the previous GZS3 methods on standard benchmarks, including PASCAL VOC, COCO-Stuff, and CATARACTS, demonstrating its effectiveness.
Vision-language models like CLIP excel at recognizing the single, prominent object in a scene. However, they struggle in complex scenes containing multiple objects. We identify a fundamental reason behind this limitation: VLMs features space exhibits significant semantic entanglement, where features of one class contain substantial information about other unrelated classes, a phenomenon we term mutual feature information (MFI). This entanglement becomes evident during class-specific queries, as unrelated objects are activated alongside the queried class. To address this limitation, we propose DCLIP, a framework that disentangles CLIP features using two complementary objectives: a novel MFI Loss that orthogonalizes the text (class) features to reduce inter-class similarity, and the Asymmetric Loss (ASL) that aligns image features with the disentangled text features. Our experiment demonstrates that DCLIP reduces inter-class feature similarity by 30\% compared to CLIP, leading to significant performance gains on multi-label recognition (MLR) and zero-shot semantic segmentation (ZS3). In MLR, DCLIP outperforms SOTA approaches on VOC2007 and COCO-14 while using 75\% fewer parameters, and surpasses SOTA ZS3 methods by 3.4 mIoU on VOC2012 and 2.8 mIoU on COCO-17. These results establish feature disentanglement as a critical factor for effective multi-object perception in vision-language models.
CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose FLAIR, Fine-grained Language-informed Image Representations, an approach that utilizes long and detailed image descriptions to learn localized image embeddings. By sampling diverse sub-captions that describe fine-grained details about an image, we train our vision-language model to produce not only global embeddings but also text-specific image representations. Our model introduces text-conditioned attention pooling on top of local image tokens to produce fine-grained image representations that excel at retrieving detailed image content. We achieve state-of-the-art performance on both, existing multimodal retrieval benchmarks, as well as, our newly introduced fine-grained retrieval task which evaluates vision-language models' ability to retrieve partial image content. Furthermore, our experiments demonstrate the effectiveness of FLAIR trained on 30M image-text pairs in capturing fine-grained visual information, including zero-shot semantic segmentation, outperforming models trained on billions of pairs. Code is available at https://github.com/ExplainableML/flair .
Semantic segmentation is a critical technique for effective scene understanding. Traditional RGB-T semantic segmentation models often struggle to generalize across diverse scenarios due to their reliance on pretrained models and predefined categories. Recent advancements in Visual Language Models (VLMs) have facilitated a shift from closed-set to open-vocabulary semantic segmentation methods. However, these models face challenges in dealing with intricate scenes, primarily due to the heterogeneity between RGB and thermal modalities. To address this gap, we present Open-RGBT, a novel open-vocabulary RGB-T semantic segmentation model. Specifically, we obtain instance-level detection proposals by incorporating visual prompts to enhance category understanding. Additionally, we employ the CLIP model to assess image-text similarity, which helps correct semantic consistency and mitigates ambiguities in category identification. Empirical evaluations demonstrate that Open-RGBT achieves superior performance in diverse and challenging real-world scenarios, even in the wild, significantly advancing the field of RGB-T semantic segmentation.
Grounding DINO and the Segment Anything Model (SAM) have achieved impressive performance in zero-shot object detection and image segmentation, respectively. Together, they have a great potential to revolutionize applications in zero-shot semantic segmentation or data annotation. Yet, in specialized domains like medical image segmentation, objects of interest (e.g., organs, tissues, and tumors) may not fall in existing class names. To address this problem, the referring expression comprehension (REC) ability of Grounding DINO is leveraged to detect arbitrary targets by their language descriptions. However, recent studies have highlighted severe limitation of the REC framework in this application setting owing to its tendency to make false positive predictions when the target is absent in the given image. And, while this bottleneck is central to the prospect of open-set semantic segmentation, it is still largely unknown how much improvement can be achieved by studying the prediction errors. To this end, we perform empirical studies on six publicly available datasets across different domains and reveal that these errors consistently follow a predictable pattern and can, thus, be mitigated by a simple strategy. Specifically, we show that false positive detections with appreciable confidence scores generally occupy large image areas and can usually be filtered by their relative sizes. More importantly, we expect these observations to inspire future research in improving REC-based detection and automated segmentation. Meanwhile, we evaluate the performance of SAM on multiple datasets from various specialized domains and report significant improvements in segmentation performance and annotation time savings over manual approaches.
In recent years, there has been a surge of interest in open-vocabulary 3D scene reconstruction facilitated by visual language models (VLMs), which showcase remarkable capabilities in open-set retrieval. However, existing methods face some limitations: they either focus on learning point-wise features, resulting in blurry semantic understanding, or solely tackle object-level reconstruction, thereby overlooking the intricate details of the object's interior. To address these challenges, we introduce OpenObj, an innovative approach to build open-vocabulary object-level Neural Radiance Fields (NeRF) with fine-grained understanding. In essence, OpenObj establishes a robust framework for efficient and watertight scene modeling and comprehension at the object-level. Moreover, we incorporate part-level features into the neural fields, enabling a nuanced representation of object interiors. This approach captures object-level instances while maintaining a fine-grained understanding. The results on multiple datasets demonstrate that OpenObj achieves superior performance in zero-shot semantic segmentation and retrieval tasks. Additionally, OpenObj supports real-world robotics tasks at multiple scales, including global movement and local manipulation.
Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised image segmentation, they significantly lag behind supervised models. In this paper, we use a diffusion UNet encoder as a foundation vision encoder and introduce DiffCut, an unsupervised zero-shot segmentation method that solely harnesses the output features from the final self-attention block. Through extensive experimentation, we demonstrate that the utilization of these diffusion features in a graph based segmentation algorithm, significantly outperforms previous state-of-the-art methods on zero-shot segmentation. Specifically, we leverage a recursive Normalized Cut algorithm that softly regulates the granularity of detected objects and produces well-defined segmentation maps that precisely capture intricate image details. Our work highlights the remarkably accurate semantic knowledge embedded within diffusion UNet encoders that could then serve as foundation vision encoders for downstream tasks. Project page at https://diffcut-segmentation.github.io
Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features from the last layer to align with text embeddings, while they neglect the crucial information in intermediate layers that contain rich object details. However, we find that directly aggregating the multi-level visual features weakens the zero-shot ability for novel classes. The large differences between the visual features from different layers make these features hard to align well with the text embeddings. We resolve this problem by introducing a series of independent decoders to align the multi-level visual features with the text embeddings in a cascaded way, forming a novel but simple framework named Cascade-CLIP. Our Cascade-CLIP is flexible and can be easily applied to existing zero-shot semantic segmentation methods. Experimental results show that our simple Cascade-CLIP achieves superior zero-shot performance on segmentation benchmarks, like COCO-Stuff, Pascal-VOC, and Pascal-Context. Our code is available at: https://github.com/HVision-NKU/Cascade-CLIP
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 present a new method to automatically generate semantic segmentation annotations for thermal imagery captured from an aerial vehicle by utilizing satellite-derived data products alongside onboard global positioning and attitude estimates. This new capability overcomes the challenge of developing thermal semantic perception algorithms for field robots due to the lack of annotated thermal field datasets and the time and costs of manual annotation, enabling precise and rapid annotation of thermal data from field collection efforts at a massively-parallelizable scale. By incorporating a thermal-conditioned refinement step with visual foundation models, our approach can produce highly-precise semantic segmentation labels using low-resolution satellite land cover data for little-to-no cost. It achieves 98.5% of the performance from using costly high-resolution options and demonstrates between 70-160% improvement over popular zero-shot semantic segmentation methods based on large vision-language models currently used for generating annotations for RGB imagery. Code will be available at: https://github.com/connorlee77/aerial-auto-segment.
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.
Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent works attempt to achieve zeroshot semantic segmentation while requiring either large-scale training or additional image/pixel level annotations. In this work, we generate free annotations for any semantic segmentation dataset using existing foundation models. We use CLIP to detect objects and SAM to generate high quality object masks. Next, we build a lightweight module on top of a self-supervised vision encoder, DinoV2, to align the patch features with a pretrained text encoder for zeroshot semantic segmentation. Our approach can bring language-based semantics to any pretrained vision encoder with minimal training, uses foundation models as the sole source of supervision and generalizes from little training data with no annotation.
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.
Zero-shot neural scene segmentation, which reconstructs 3D neural segmentation field without manual annotations, serves as an effective way for scene understanding. However, existing models, especially the efficient 3D Gaussian-based methods, struggle to produce compact segmentation results. This issue stems primarily from their redundant learnable attributes assigned on individual Gaussians, leading to a lack of robustness against the 3D-inconsistencies in zero-shot generated raw labels. To address this problem, our work, named Compact Segmented 3D Gaussians (CoSegGaussians), proposes the Feature Unprojection and Fusion module as the segmentation field, which utilizes a shallow decoder generalizable for all Gaussians based on high-level features. Specifically, leveraging the learned Gaussian geometric parameters, semantic-aware image-based features are introduced into the scene via our unprojection technique. The lifted features, together with spatial information, are fed into the multi-scale aggregation decoder to generate segmentation identities for all Gaussians. Furthermore, we design CoSeg Loss to boost model robustness against 3D-inconsistent noises. Experimental results show that our model surpasses baselines on zero-shot semantic segmentation task, improving by ~10% mIoU over the best baseline. Code and more results will be available at https://David-Dou.github.io/CoSegGaussians.
Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks. The present landscape features two-stage methodologies beset by issues such as intricate pipelines and elevated computational costs. While current one-stage approaches alleviate these concerns and incorporate Visual Prompt Training (VPT) to uphold CLIP's generalization capacity, they still fall short in fully harnessing CLIP's potential for pixel-level unseen class demarcation and precise pixel predictions. To further stimulate CLIP's zero-shot dense prediction capability, we propose SPT-SEG, a one-stage approach that improves CLIP's adaptability from image to pixel. Specifically, we initially introduce Spectral Prompt Tuning (SPT), incorporating spectral prompts into the CLIP visual encoder's shallow layers to capture structural intricacies of images, thereby enhancing comprehension of unseen classes. Subsequently, we introduce the Spectral Guided Decoder (SGD), utilizing both high and low-frequency information to steer the network's spatial focus towards more prominent classification features, enabling precise pixel-level prediction outcomes. Through extensive experiments on two public datasets, we demonstrate the superiority of our method over state-of-the-art approaches, performing well across all classes and particularly excelling in handling unseen classes. Code is available at:https://github.com/clearxu/SPT.
Addressing Out-Of-Distribution (OOD) Segmentation and Zero-Shot Semantic Segmentation (ZS3) is challenging, necessitating segmenting unseen classes. Existing strategies adapt the class-agnostic Mask2Former (CA-M2F) tailored to specific tasks. However, these methods cater to singular tasks, demand training from scratch, and we demonstrate certain deficiencies in CA-M2F, which affect performance. We propose the Class-Agnostic Structure-Constrained Learning (CSL), a plug-in framework that can integrate with existing methods, thereby embedding structural constraints and achieving performance gain, including the unseen, specifically OOD, ZS3, and domain adaptation (DA) tasks. There are two schemes for CSL to integrate with existing methods (1) by distilling knowledge from a base teacher network, enforcing constraints across training and inference phrases, or (2) by leveraging established models to obtain per-pixel distributions without retraining, appending constraints during the inference phase. We propose soft assignment and mask split methodologies that enhance OOD object segmentation. Empirical evaluations demonstrate CSL's prowess in boosting the performance of existing algorithms spanning OOD segmentation, ZS3, and DA segmentation, consistently transcending the state-of-art across all three tasks.
Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention, we surprisingly find that CLIP can adapt to dense prediction tasks by simply introducing a novel Correlative Self-Attention (CSA) mechanism. Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation. Extensive experiments show the advantage of CSA: we obtain a 38.2% average zero-shot mIoU across eight semantic segmentation benchmarks highlighted in this paper, significantly outperforming the existing SoTA's 33.9% and the vanilla CLIP's 14.1%.
While semantic segmentation has seen tremendous improvements in the past, there are still significant labeling efforts necessary and the problem of limited generalization to classes that have not been present during training. To address this problem, zero-shot semantic segmentation makes use of large self-supervised vision-language models, allowing zero-shot transfer to unseen classes. In this work, we build a benchmark for Multi-domain Evaluation of Semantic Segmentation (MESS), which allows a holistic analysis of performance across a wide range of domain-specific datasets such as medicine, engineering, earth monitoring, biology, and agriculture. To do this, we reviewed 120 datasets, developed a taxonomy, and classified the datasets according to the developed taxonomy. We select a representative subset consisting of 22 datasets and propose it as the MESS benchmark. We evaluate eight recently published models on the proposed MESS benchmark and analyze characteristics for the performance of zero-shot transfer models. The toolkit is available at https://github.com/blumenstiel/MESS.