Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation

• URL: http://arxiv.org/abs/2411.19331v1
• Date: Thu, 28 Nov 2024 19:00:03 GMT
• Title: Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation
• Authors: Luca Barsellotti, Lorenzo Bianchi, Nicola Messina, Fabio Carrara, Marcella Cornia, Lorenzo Baraldi, Fabrizio Falchi, Rita Cucchiara,
• Abstract summary: We present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks.
• Score: 43.69036787338244
• License:
• Abstract: Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks. Source code and models are publicly available at: https://lorebianchi98.github.io/Talk2DINO/.

Related papers

• DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment [20.953645420787527]
  We train a CLIP-like model with only a fraction of the computational cost compared to CLIP. We achieve state-of-the-art results in zero-shot classification and open-vocabulary semantic segmentation.
  arXiv  Detail & Related papers  (2024-12-20T20:46:48Z)
• Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels [53.8817160001038]
  We propose a novel method, PixelCLIP, to adapt the CLIP image encoder for pixel-level understanding. To address the challenges of leveraging masks without semantic labels, we devise an online clustering algorithm. PixelCLIP shows significant performance improvements over CLIP and competitive results compared to caption-supervised methods.
  arXiv  Detail & Related papers  (2024-09-30T01:13:03Z)
• Selective Vision-Language Subspace Projection for Few-shot CLIP [55.361337202198925]
  We introduce a method called Selective Vision-Language Subspace Projection (SSP) SSP incorporates local image features and utilizes them as a bridge to enhance the alignment between image-text pairs. Our approach entails only training-free matrix calculations and can be seamlessly integrated into advanced CLIP-based few-shot learning frameworks.
  arXiv  Detail & Related papers  (2024-07-24T03:45:35Z)
• O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation [9.431926560072412]
  We propose O2V-mapping, which utilizes voxel-based language and geometric features to create an open-vocabulary field. Experiments on open-vocabulary object localization and semantic segmentation demonstrate that O2V-mapping achieves online construction of language scenes.
  arXiv  Detail & Related papers  (2024-04-10T08:54:43Z)
• Panoptic Vision-Language Feature Fields [27.209602602110916]
  We propose the first algorithm for open-vocabulary panoptic segmentation in 3D scenes. Our algorithm learns a semantic feature field of the scene by distilling vision-language features from a pretrained 2D model. Our method achieves panoptic segmentation performance similar to the state-of-the-art closed-set 3D systems on the HyperSim, ScanNet and Replica dataset.
  arXiv  Detail & Related papers  (2023-09-11T13:41:27Z)
• GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation [52.65506307440127]
  We propose GeoVLN, which learns Geometry-enhanced visual representation based on slot attention for robust Visual-and-Language Navigation. We employ V&L BERT to learn a cross-modal representation that incorporate both language and vision informations.
  arXiv  Detail & Related papers  (2023-05-26T17:15:22Z)
• Learning video embedding space with Natural Language Supervision [1.6822770693792823]
  We propose a novel approach to map video embedding space to natural langugage. We propose a two-stage approach that first extracts visual features from each frame of a video using a pre-trained CNN, and then uses the CLIP model to encode the visual features for the video domain.
  arXiv  Detail & Related papers  (2023-03-25T23:24:57Z)
• SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation [26.079055078561986]
  We propose a CLIP-based model named SegCLIP for the topic of open-vocabulary segmentation. The main idea is to gather patches with learnable centers to semantic regions through training on text-image pairs. Experimental results show that our model achieves comparable or superior segmentation accuracy.
  arXiv  Detail & Related papers  (2022-11-27T12:38:52Z)
• ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting [121.11880210592497]
  We argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input. We propose an autonomous, bidirectional and iterative ABINet++ for scene text spotting.
  arXiv  Detail & Related papers  (2022-11-19T03:50:33Z)
• From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network [70.47504933083218]
  We propose a Visual Language Modeling Network (VisionLAN), which views the visual and linguistic information as a union. VisionLAN significantly improves the speed by 39% and adaptively considers the linguistic information to enhance the visual features for accurate recognition.
  arXiv  Detail & Related papers  (2021-08-22T07:56:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.