Spatial Semantic Recurrent Mining for Referring Image Segmentation

• URL: http://arxiv.org/abs/2405.09006v1
• Date: Wed, 15 May 2024 00:17:48 GMT
• Title: Spatial Semantic Recurrent Mining for Referring Image Segmentation
• Authors: Jiaxing Yang, Lihe Zhang, Jiayu Sun, Huchuan Lu,
• Abstract summary: We propose Stextsuperscript2RM to achieve high-quality cross-modality fusion. It follows a working strategy of trilogy: distributing language feature, spatial semantic recurrent coparsing, and parsed-semantic balancing. Our proposed method performs favorably against other state-of-the-art algorithms.
• Score: 63.34997546393106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Referring Image Segmentation (RIS) consistently requires language and appearance semantics to more understand each other. The need becomes acute especially under hard situations. To achieve, existing works tend to resort to various trans-representing mechanisms to directly feed forward language semantic along main RGB branch, which however will result in referent distribution weakly-mined in space and non-referent semantic contaminated along channel. In this paper, we propose Spatial Semantic Recurrent Mining (S\textsuperscript{2}RM) to achieve high-quality cross-modality fusion. It follows a working strategy of trilogy: distributing language feature, spatial semantic recurrent coparsing, and parsed-semantic balancing. During fusion, S\textsuperscript{2}RM will first generate a constraint-weak yet distribution-aware language feature, then bundle features of each row and column from rotated features of one modality context to recurrently correlate relevant semantic contained in feature from other modality context, and finally resort to self-distilled weights to weigh on the contributions of different parsed semantics. Via coparsing, S\textsuperscript{2}RM transports information from the near and remote slice layers of generator context to the current slice layer of parsed context, capable of better modeling global relationship bidirectional and structured. Besides, we also propose a Cross-scale Abstract Semantic Guided Decoder (CASG) to emphasize the foreground of the referent, finally integrating different grained features at a comparatively low cost. Extensive experimental results on four current challenging datasets show that our proposed method performs favorably against other state-of-the-art algorithms.

Related papers

• Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation [9.109484087832058]
  The goal of referring remote sensing image segmentation (RRSIS) is to generate a pixel-level mask of the target object identified by the referring expression. To address the aforementioned challenges, a novel RRSIS framework is proposed, termed the cross-modal bidirectional interaction model (CroBIM) To further forster the research of RRSIS, we also construct RISBench, a new large-scale benchmark dataset comprising 52,472 image-language-label triplets.
  arXiv  Detail & Related papers  (2024-10-11T08:28:04Z)
• BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval [54.66399120084227]
  We propose a novel method to improve the generalization of dense retrieval via capturing matching signal called BERM. Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
  arXiv  Detail & Related papers  (2023-05-18T15:43:09Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation [102.25240608024063]
  Referring image segments an image from a language expression. We develop an algorithm that shifts from being localization-centric to segmentation-language. Compared to its counterparts, our method is more versatile yet effective.
  arXiv  Detail & Related papers  (2023-03-11T08:42:40Z)
• Asymmetric Cross-Scale Alignment for Text-Based Person Search [15.618984100653348]
  Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment. We present a transformer-based model to extract multi-scale representations, and perform Asymmetric Cross-Scale Alignment (ACSA) to precisely align the two modalities.
  arXiv  Detail & Related papers  (2022-11-26T08:34:35Z)
• Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation [25.231470587575238]
  We propose regional semantic contrast and aggregation (RCA) for learning semantic segmentation. RCA is equipped with a regional memory bank to store massive, diverse object patterns appearing in training data. RCA earns a strong capability of fine-grained semantic understanding, and eventually establishes new state-of-the-art results on two popular benchmarks.
  arXiv  Detail & Related papers  (2022-03-17T23:29:03Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation [44.792859259093085]
  We aim to enable the low-level feature to aggregate the complementary context from adjacent high-level feature maps by a cross-scale pixel-to-region operation. We employ an efficient feature pyramid network to obtain multi-scale features. Experiment results show that the RSP head performs competitively on both semantic segmentation and panoptic segmentation with high efficiency.
  arXiv  Detail & Related papers  (2021-06-03T10:49:48Z)
• Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation [66.85202434812942]
  We reformulate few-shot segmentation as a semantic reconstruction problem. We convert base class features into a series of basis vectors which span a class-level semantic space for novel class reconstruction. Our proposed approach, referred to as anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems.
  arXiv  Detail & Related papers  (2021-06-01T02:17:36Z)

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.