Focusing On Targets For Improving Weakly Supervised Visual Grounding

• URL: http://arxiv.org/abs/2302.11252v1
• Date: Wed, 22 Feb 2023 10:02:21 GMT
• Title: Focusing On Targets For Improving Weakly Supervised Visual Grounding
• Authors: Viet-Quoc Pham, Nao Mishima
• Abstract summary: Weakly supervised visual grounding aims to predict the region in an image that corresponds to a specific linguistic query. The state-of-the-art method uses a vision language pre-training model to acquire heatmaps from Grad-CAM. We propose two simple but efficient methods for improving this approach.
• Score: 1.5686134908061993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weakly supervised visual grounding aims to predict the region in an image that corresponds to a specific linguistic query, where the mapping between the target object and query is unknown in the training stage. The state-of-the-art method uses a vision language pre-training model to acquire heatmaps from Grad-CAM, which matches every query word with an image region, and uses the combined heatmap to rank the region proposals. In this paper, we propose two simple but efficient methods for improving this approach. First, we propose a target-aware cropping approach to encourage the model to learn both object and scene level semantic representations. Second, we apply dependency parsing to extract words related to the target object, and then put emphasis on these words in the heatmap combination. Our method surpasses the previous SOTA methods on RefCOCO, RefCOCO+, and RefCOCOg by a notable margin.

Related papers

• Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehension [40.21084218601082]
  This paper focuses on a challenging setup where target localization is learned directly from image-text pairs. We propose a novel Progressive Network (PCNet) to leverage target-related textual cues for progressively localizing the target object. Our method outperforms SOTA methods on three common benchmarks.
  arXiv  Detail & Related papers  (2024-10-02T13:30:32Z)
• AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization [57.34659640776723]
  We propose an end-to-end framework named AddressCLIP to solve the problem with more semantics. We have built three datasets from Pittsburgh and San Francisco on different scales specifically for the IAL problem.
  arXiv  Detail & Related papers  (2024-07-11T03:18:53Z)
• ScanFormer: Referring Expression Comprehension by Iteratively Scanning [11.95137121280909]
  Referring Expression (REC) aims to localize the target objects specified by free-form natural language descriptions in images. While state-of-the-art methods achieve impressive performance, they perform a dense perception of images, which incorporates redundant visual regions unrelated to linguistic queries. This inspires us to explore a question: can we eliminate linguistic-irrelevant redundant visual regions to improve the efficiency of the model?
  arXiv  Detail & Related papers  (2024-06-26T03:56:03Z)
• Mapping High-level Semantic Regions in Indoor Environments without Object Recognition [50.624970503498226]
  The present work proposes a method for semantic region mapping via embodied navigation in indoor environments. To enable region identification, the method uses a vision-to-language model to provide scene information for mapping. By projecting egocentric scene understanding into the global frame, the proposed method generates a semantic map as a distribution over possible region labels at each location.
  arXiv  Detail & Related papers  (2024-03-11T18:09:50Z)
• Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation [37.15828464616587]
  Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation. We propose a novel Question-Answer Cross-Language-Image Matching framework for WSSS (QA-CLIMS)
  arXiv  Detail & Related papers  (2024-01-18T10:55:13Z)
• 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)
• Joint Visual Grounding and Tracking with Natural Language Specification [6.695284124073918]
  Tracking by natural language specification aims to locate the referred target in a sequence based on the natural language description. We propose a joint visual grounding and tracking framework, which reformulates grounding and tracking as a unified task. Our method performs favorably against state-of-the-art algorithms for both tracking and grounding.
  arXiv  Detail & Related papers  (2023-03-21T17:09:03Z)
• Complex Scene Image Editing by Scene Graph Comprehension [17.72638225034884]
  We propose a two-stage method for achieving complex scene image editing by Scene Graph (SGC-Net) In the first stage, we train a Region of Interest (RoI) prediction network that uses scene graphs and predict the locations of the target objects. The second stage uses a conditional diffusion model to edit the image based on our RoI predictions.
  arXiv  Detail & Related papers  (2022-03-24T05:12:54Z)
• RegionCLIP: Region-based Language-Image Pretraining [94.29924084715316]
  Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification. We propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visual representations. Our method significantly outperforms the state of the art by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets.
  arXiv  Detail & Related papers  (2021-12-16T18:39:36Z)
• SIRI: Spatial Relation Induced Network For Spatial Description Resolution [64.38872296406211]
  We propose a novel relationship induced (SIRI) network for language-guided localization. We show that our method is around 24% better than the state-of-the-art method in terms of accuracy, measured by an 80-pixel radius. Our method also generalizes well on our proposed extended dataset collected using the same settings as Touchdown.
  arXiv  Detail & Related papers  (2020-10-27T14:04:05Z)
• Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [128.03739769844736]
  Two neural co-attentions are incorporated into the classifier to capture cross-image semantic similarities and differences. In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference. Our algorithm sets new state-of-the-arts on all these settings, demonstrating well its efficacy and generalizability.
  arXiv  Detail & Related papers  (2020-07-03T21:53:46Z)

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.