FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models
DIISM University of Siena（DIISM锡耶纳大学）；CNRS, ISIR Sorbonne University（CNRS，ISIR索邦大学）；Inria, ARCHES Sorbonne University（Inria，ARCHES索邦大学）；Valeo.ai Sorbonne University（Valeo.ai索邦大学）
Barbara Toniella Corradini, Mustafa Shukor, Paul Couairon, Guillaume Couairon, Franco Scarselli, Matthieu Cord
发表信息：
Proceedings of the 2025 International Joint Conference on Neural Networks (IJCNN 2025)
Foundation models have exhibited unprecedented capabilities in tackling many domains and tasks. Models such as CLIP are currently widely used to bridge cross-modal representations, and text-to-image diffusion models are arguably the leading models in terms of realistic image generation. Image generative models are trained on massive datasets that provide them with powerful internal spatial representations. In this work, we explore the potential benefits of such representations, beyond image generation, in particular, for dense visual prediction tasks. We focus on the task of image segmentation, which is traditionally solved by training models on closed-vocabulary datasets, with pixel-level annotations. To avoid the annotation cost or training large diffusion models, we constraint our setup to be zero-shot and training-free. In a nutshell, our pipeline leverages different and relatively small-sized, open-source foundation models for zero-shot open-vocabulary segmentation. The pipeline is as follows: the image is passed to both a captioner model (i.e. BLIP) and a diffusion model (i.e., Stable Diffusion Model) to generate a text description and visual representation, respectively. The features are clustered and binarized to obtain class agnostic masks for each object. These masks are then mapped to a textual class, using the CLIP model to support open-vocabulary. Finally, we add a refinement step that allows to obtain a more precise segmentation mask. Our approach (dubbed FreeSeg-Diff), which does not rely on any training, outperforms many training-based approaches on both Pascal VOC and COCO datasets. In addition, we show very competitive results compared to the recent weakly-supervised segmentation approaches. We provide comprehensive experiments showing the superiority of diffusion model features compared to other pretrained models. Project page: https://bcorrad.github.io/freesegdiff/
FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；ByteDance Inc（字节跳动公司）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024
University of Science and Technology of China（中国科学技术大学）；Zhejiang University（浙江大学）；Northwestern Polytechnical University（西北工业大学）；Northwest University（西北大学）
O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation
Academy for Engineering & Technology（工程与技术学院）；Fudan University（复旦大学）；State Key Laboratory of Intelligent Vehicle Safety Technology（智能车辆安全技术国家重点实验室）；School of Future Technology（未来技术学院）；Harbin Institute of Technology（哈尔滨工业大学）；Department of Computer Science and Engineering（计算机科学与工程系）；Shanghai Jiao Tong University（上海交通大学）
Current point-cloud detection methods have difficulty detecting the open-vocabulary objects in the real world, due to their limited generalization capability. Moreover, it is extremely laborious and expensive to collect and fully annotate a point-cloud detection dataset with numerous classes of objects, leading to the limited classes of existing point-cloud datasets and hindering the model to learn general representations to achieve open-vocabulary point-cloud detection. As far as we know, we are the first to study the problem of open-vocabulary 3D point-cloud detection. Instead of seeking a p…
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabul…
School of Electronic Information, Wuhan University of Science and Technology（武汉科技大学电子信息学院）；State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室）；Oriental Space Port Research Institute（东方航天港研究院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）
The Hong Kong University of Science and Technology（香港科技大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Tsinghua University（清华大学）；Microsoft Research at Redmond（微软雷德蒙德研究院）
We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets. To bridge the gap of vocabulary and annotation granularity, we first introduce a pre-trained text encoder to encode all the visual concepts in two tasks and learn a common semantic space for them. This gives us reasonably good results compared with the counterparts trained on segmentation task only. To further reconcile them, we locate two discrepancies: $i$) task discrepancy -- segmentation requires extracting masks for both foreground obje…
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
Tianjin University（天津大学）；Chongqing University（重庆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
LarvSeg: Exploring Image Classification Data For Large Vocabulary Semantic Segmentation via Category-wise Attentive Classifier
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Center of Data Science, Peking University（北京大学数据科学中心）；Microsoft Research Asia（微软亚洲研究院）
Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）
Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision. We note that both these modes of supervision are not optimally aligned for the detection task: CLIP is trained with image-text pairs and lacks precise localization of objects while the image-level supervision has been used with heuristics that do not accurately specify local …
Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion
The Hong Kong University of Science and Technology（香港科学与技术大学）；CFAR & IHPC, A*STAR（CFAR与IHPC，A*STAR）；Deakin University（德克萨斯大学）；Nankai University（南开大学）；National University of Singapore（新加坡国立大学）；Trinity College Dublin（都柏林大学）
We propose an approach for annotating object classes using free-form text written by undirected and untrained annotators. Free-form labeling is natural for annotators, they intuitively provide very specific and exhaustive labels, and no training stage is necessary. We first collect 729 labels on 15k images using 124 different annotators. Then we automatically enrich the structure of these free-form annotations by discovering a natural vocabulary of 4020 classes within them. This vocabulary represents the natural distribution of objects well and is learned directly from data, instead of being a…
One of the prevalent learning tasks involving images is content-based image classification. This is a difficult task especially because the low-level features used to digitally describe images usually capture little information about the semantics of the images. In this paper, we tackle this difficulty by enriching the semantic content of the image representation by using external knowledge. The underlying hypothesis of our work is that creating a more semantically rich representation for images would yield higher machine learning performances, without the need to modify the learning algorithm…
