A Simple Framework for Open-Vocabulary Zero-Shot Segmentation

• URL: http://arxiv.org/abs/2406.16085v2
• Date: Mon, 1 Jul 2024 06:33:12 GMT
• Title: A Simple Framework for Open-Vocabulary Zero-Shot Segmentation
• Authors: Thomas Stegmüller, Tim Lebailly, Nikola Dukic, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran,
• Abstract summary: SimZSS is a framework for open-vocabulary Zero-Shot segmentation. It exploits the discrete nature of text and linguistic knowledge to pinpoint local concepts within captions. SimZSS achieves state-of-the-art results on 7 out of 8 benchmark datasets in less than 15 minutes.
• Score: 36.01531912271202
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle in dense tasks like zero-shot open-vocabulary segmentation. This deficiency is often attributed to the absence of localization cues in captions and the intertwined nature of the learning process, which encompasses both image representation learning and cross-modality alignment. To tackle these issues, we propose SimZSS, a Simple framework for open-vocabulary Zero-Shot Segmentation. The method is founded on two key principles: i) leveraging frozen vision-only models that exhibit spatial awareness while exclusively aligning the text encoder and ii) exploiting the discrete nature of text and linguistic knowledge to pinpoint local concepts within captions. By capitalizing on the quality of the visual representations, our method requires only image-caption pairs datasets and adapts to both small curated and large-scale noisy datasets. When trained on COCO Captions across 8 GPUs, SimZSS achieves state-of-the-art results on 7 out of 8 benchmark datasets in less than 15 minutes.

Related papers

• CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification [9.996589403019675]
  Person re-identification (ReID) has recently benefited from large pretrained vision-language models such as Contrastive Language-Image Pre-Training (CLIP) We propose one straightforward solution by leveraging existing image captioning models to generate pseudo captions for person images. We introduce CLIP-SCGI, a framework that leverages synthesized captions to guide the learning of discriminative and robust representations.
  arXiv  Detail & Related papers  (2024-10-12T06:24:33Z)
• Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training [14.340740609933437]
  We propose a novel zero-shot image captioning framework with text-only training to reduce the modality gap. In particular, we introduce a subregion feature aggregation to leverage local region information. We extend our framework to build a zero-shot VQA pipeline, demonstrating its generality.
  arXiv  Detail & Related papers  (2024-01-04T16:43:46Z)
• Grounding Everything: Emerging Localization Properties in Vision-Language Transformers [51.260510447308306]
  We show that pretrained vision-language (VL) models allow for zero-shot open-vocabulary object localization without any fine-tuning. We propose a Grounding Everything Module (GEM) that generalizes the idea of value-value attention introduced by CLIPSurgery to a self-self attention path. We evaluate the proposed GEM framework on various benchmark tasks and datasets for semantic segmentation.
  arXiv  Detail & Related papers  (2023-12-01T19:06:12Z)
• SILC: Improving Vision Language Pretraining with Self-Distillation [113.50400246862056]
  We introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contrastive learning with the simple addition of local-to-global correspondence learning by self-distillation. We show that distilling local image features from an exponential moving average (EMA) teacher model significantly improves model performance on dense predictions tasks like detection and segmentation.
  arXiv  Detail & Related papers  (2023-10-20T08:44:47Z)
• Exploring Open-Vocabulary Semantic Segmentation without Human Labels [76.15862573035565]
  We present ZeroSeg, a novel method that leverages the existing pretrained vision-language model (VL) to train semantic segmentation models. ZeroSeg overcomes this by distilling the visual concepts learned by VL models into a set of segment tokens, each summarizing a localized region of the target image. Our approach achieves state-of-the-art performance when compared to other zero-shot segmentation methods under the same training data.
  arXiv  Detail & Related papers  (2023-06-01T08:47:06Z)
• Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [44.17304848026688]
  We present ODISE: Open-vocabulary DIffusion-based panoptic SEgmentation. It unifies pre-trained text-image diffusion and discriminative models to perform open-vocabulary segmentation. Our approach outperforms the previous state of the art by significant margins on both open-vocabulary panoptic and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2023-03-08T18:58:26Z)
• Cross-modal Representation Learning for Zero-shot Action Recognition [67.57406812235767]
  We present a cross-modal Transformer-based framework, which jointly encodes video data and text labels for zero-shot action recognition (ZSAR) Our model employs a conceptually new pipeline by which visual representations are learned in conjunction with visual-semantic associations in an end-to-end manner. Experiment results show our model considerably improves upon the state of the arts in ZSAR, reaching encouraging top-1 accuracy on UCF101, HMDB51, and ActivityNet benchmark datasets.
  arXiv  Detail & Related papers  (2022-05-03T17:39:27Z)
• A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model [61.58071099082296]
  It is unclear how to make zero-shot recognition working well on broader vision problems, such as object detection and semantic segmentation. In this paper, we target for zero-shot semantic segmentation, by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. Our experimental results show that this simple framework surpasses previous state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2021-12-29T18:56:18Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)

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.