The supplementary material is organized as follows:1 Implementation Details.(Sec. Except for the Object Mask Prompt and Compositional Prompt Tuning designs,7 we follow the default architecture in the original ZSseg paper. The number of part queries is set to 50.8 All the two-stage baselines are trained with AdamW optimizer with the initial learning rate of 1e-49 and weight decay of 1e-4. A poly learning rate policy with a power of 0.9is adopted.

Furthermore, the large-scale vision and language models, which play a key role in the open vocabulary setting, struggle to recognize parts as effectively as objects. To comprehensively investigate and tackle these challenges, we propose an Open-Vocabulary Part Segmentation (OV-PARTS) benchmark. OV-PARTS includes refined versions of two publicly available datasets: Pascal-Part-116 and ADE20K-Part-234.

The number of part queries is set to 50. SGD optimizer with the initial learning rate of 2e-2 and weight decay of 5e-4 is used. We sample 128 training samples for each object part class. The initial value of the learnable fusion weight is 0.5 . The total batch size is 8, and the training iterations amount to 40k.

OV -P ARTS includes refined versions of two publicly available datasets: Pascal-Part-116 and ADE20K-Part-234.

Real-time aerial image segmentation plays an important role in the environmental perception of Uncrewed Aerial Vehicles (UAVs). We introduce BlabberSeg, an optimized Vision-Language Model built on CLIPSeg for on-board, real-time processing of aerial images by UAVs. BlabberSeg improves the efficiency of CLIPSeg by reusing prompt and model features, reducing computational overhead while achieving real-time open-vocabulary aerial segmentation. We validated BlabberSeg in a safe landing scenario using the Dynamic Open-Vocabulary Enhanced SafE-Landing with Intelligence (DOVESEI) framework, which uses visual servoing and open-vocabulary segmentation. BlabberSeg reduces computational costs significantly, with a speed increase of 927.41% (16.78 Hz) on a NVIDIA Jetson Orin AGX (64GB) compared with the original CLIPSeg (1.81Hz), achieving real-time aerial segmentation with negligible loss in accuracy (2.1% as the ratio of the correctly segmented area with respect to CLIPSeg). BlabberSeg's source code is open and available online.

Vision-Language Models (VLMs) have shown impressive performance in vision tasks, but adapting them to new domains often requires expensive fine-tuning. Prompt tuning techniques, including textual, visual, and multimodal prompting, offer efficient alternatives by leveraging learnable prompts. However, their application to Vision-Language Segmentation Models (VLSMs) and evaluation under significant domain shifts remain unexplored. This work presents an open-source benchmarking framework, TuneVLSeg, to integrate various unimodal and multimodal prompt tuning techniques into VLSMs, making prompt tuning usable for downstream segmentation datasets with any number of classes. TuneVLSeg includes $6$ prompt tuning strategies on various prompt depths used in $2$ VLSMs totaling of $8$ different combinations. We test various prompt tuning on $8$ diverse medical datasets, including $3$ radiology datasets (breast tumor, echocardiograph, chest X-ray pathologies) and $5$ non-radiology datasets (polyp, ulcer, skin cancer), and two natural domain segmentation datasets. Our study found that textual prompt tuning struggles under significant domain shifts, from natural-domain images to medical data. Furthermore, visual prompt tuning, with fewer hyperparameters than multimodal prompt tuning, often achieves performance competitive to multimodal approaches, making it a valuable first attempt. Our work advances the understanding and applicability of different prompt-tuning techniques for robust domain-specific segmentation. The source code is available at https://github.com/naamiinepal/tunevlseg.

CLIPSeg generates a 22 22 64 embedding tensor, which embeds a semantic mask that aligns with the input image spatially and is conditioned on text. To maintain a consistent embedding size throughout the pipeline, we employ an MLP (bottom left MLP in Figure 1) to upscale the 64-dimensional embedding to 256 dimensions, followed by a self-attention layer, which learns interpatch correlations to focus on the relevant patches. CLIPSeg's embedding output is enhanced with Dense Positional Encoding (DPE) to ensure that the self-attention layer has access to crucial geometric information. To this end, the DPE values are added to the embedding vector even after participating in the self-attention layer. To generate our DPE, we use an identical frequency matrix as SAM. This ensures that every element within each vector of the DPE conveys consistent information, that is aligned with what SAM's decoder has been trained to interpret.

One key challenge in Augmented Reality is the placement of virtual content in natural locations. Most existing automated techniques can only work with a closed-vocabulary, fixed set of objects. In this paper, we introduce and evaluate several methods for automatic object placement using recent advances in open-vocabulary vision-language models. Through a multifaceted evaluation, we identify a new state-of-the-art method, OCTO+. We also introduce a benchmark for automatically evaluating the placement of virtual objects in augmented reality, alleviating the need for costly user studies. Through this, in addition to human evaluations, we find that OCTO+ places objects in a valid region over 70% of the time, outperforming other methods on a range of metrics.

Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models, specifically CLIP, to the domain of sound source localization. Unlike conventional approaches, we employ the pre-trained CLIP model without explicit text input, relying solely on the audio-visual correspondence. To this end, we introduce a framework that translates audio signals into tokens compatible with CLIP's text encoder, yielding audio-driven embeddings. By directly using these embeddings, our method generates audio-grounded masks for the provided audio, extracts audio-grounded image features from the highlighted regions, and aligns them with the audio-driven embeddings using the audio-visual correspondence objective. Our findings suggest that utilizing pre-trained image-text models enable our model to generate more complete and compact localization maps for the sounding objects. Extensive experiments show that our method outperforms state-of-the-art approaches by a significant margin.

Medical image segmentation with deep learning is an important and widely studied topic because segmentation enables quantifying target structure size and shape that can help in disease diagnosis, prognosis, surgery planning, and understanding. Recent advances in the foundation Vision-Language Models (VLMs) and their adaptation to segmentation tasks in natural images with Vision-Language Segmentation Models (VLSMs) have opened up a unique opportunity to build potentially powerful segmentation models for medical images that enable providing helpful information via language prompt as input, leverage the extensive range of other medical imaging datasets by pooled dataset training, adapt to new classes, and be robust against out-of-distribution data with human-in-the-loop prompting during inference. Although transfer learning from natural to medical images for imageonly segmentation models has been studied, no studies have analyzed how the joint representation of vision-language transfers to medical images in segmentation problems and understand gaps in leveraging their full potential. We present the first benchmark study on transfer learning of VLSMs to 2D medical images with thoughtfully collected 11 existing 2D medical image datasets of diverse modalities with carefully presented 9 types of language prompts from 14 attributes. Our results indicate that VLSMs trained in natural image-text pairs transfer reasonably to the medical domain in zero-shot settings when prompted appropriately for non-radiology photographic modalities; when finetuned, they obtain comparable performance to conventional architectures, even in X-rays and ultrasound modalities. However, the additional benefit of language prompts during finetuning may be limited, with image features playing a more dominant role; they can better handle training on pooled datasets combining diverse modalities and are potentially more robust to domain shift than the conventional segmentation models. The code and datasets are released at https://github.com/naamiinepal/med