Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation

• URL: http://arxiv.org/abs/2305.03944v2
• Date: Thu, 6 Jul 2023 02:43:50 GMT
• Title: Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation
• Authors: Deyi Ji, Haoran Wang, Mingyuan Tao, Jianqiang Huang, Xian-Sheng Hua, Hongtao Lu
• Abstract summary: We propose a novel Structural and Statistical Texture Knowledge Distillation (SSTKD) framework for semantic segmentation. For structural texture knowledge, we introduce a Contourlet Decomposition Module (CDM) that decomposes low-level features. For statistical texture knowledge, we propose a Denoised Texture Intensity Equalization Module (DTIEM) to adaptively extract and enhance statistical texture knowledge.
• Score: 72.67912031720358
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture knowledge is also of vital importance for characterizing the local structural pattern and global statistical property, such as boundary, smoothness, regularity and color contrast, which may not be well addressed by high-level deep features. In this paper, we are intended to take full advantage of both structural and statistical texture knowledge and propose a novel Structural and Statistical Texture Knowledge Distillation (SSTKD) framework for semantic segmentation. Specifically, for structural texture knowledge, we introduce a Contourlet Decomposition Module (CDM) that decomposes low-level features with iterative Laplacian pyramid and directional filter bank to mine the structural texture knowledge. For statistical knowledge, we propose a Denoised Texture Intensity Equalization Module (DTIEM) to adaptively extract and enhance statistical texture knowledge through heuristics iterative quantization and denoised operation. Finally, each knowledge learning is supervised by an individual loss function, forcing the student network to mimic the teacher better from a broader perspective. Experiments show that the proposed method achieves state-of-the-art performance on Cityscapes, Pascal VOC 2012 and ADE20K datasets.

Related papers

• Structure-aware Domain Knowledge Injection for Large Language Models [37.089378357827826]
  This paper introduces a pioneering methodology, termed StructTuning, to efficiently transform foundation Large Language Models (LLMs) into domain specialists. It significantly reduces the training corpus requirement to a mere 0.3%, while achieving an impressive 50% of traditional knowledge injection performance. Our method demonstrates the potential of comparable improvement against the state-of-the-art MMedLM2 on MMedBench, while significantly reducing the training costs to 5%.
  arXiv  Detail & Related papers  (2024-07-23T12:38:48Z)
• Exploring Graph-based Knowledge: Multi-Level Feature Distillation via Channels Relational Graph [8.646512035461994]
  In visual tasks, large teacher models capture essential features and deep information, enhancing performance. We propose a distillation framework based on graph knowledge, including a multi-level feature alignment strategy. We emphasize spectral embedding (SE) as a key technique in our distillation process, which merges the student's feature space with the relational knowledge and structural complexities similar to the teacher network.
  arXiv  Detail & Related papers  (2024-05-14T12:37:05Z)
• Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic [51.967603572656266]
  We introduce a consistent and theoretically grounded approach to annotating decompositional entailment. We find that our new dataset, RDTE, has a substantially higher internal consistency (+9%) than prior decompositional entailment datasets. We also find that training an RDTE-oriented entailment classifier via knowledge distillation and employing it in an entailment tree reasoning engine significantly improves both accuracy and proof quality.
  arXiv  Detail & Related papers  (2024-02-22T18:55:17Z)
• Graph-level Protein Representation Learning by Structure Knowledge Refinement [50.775264276189695]
  This paper focuses on learning representation on the whole graph level in an unsupervised manner. We propose a novel framework called Structure Knowledge Refinement (SKR) which uses data structure to determine the probability of whether a pair is positive or negative.
  arXiv  Detail & Related papers  (2024-01-05T09:05:33Z)
• EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition [27.199124692225777]
  Scene recognition based on deep-learning has made significant progress, but there are still limitations in its performance. We propose EnTri, a framework that employs ensemble learning using a hierarchy of visual features. EnTri has demonstrated superiority in terms of recognition accuracy, achieving competitive performance compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-07-23T22:11:23Z)
• StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition [49.58170209388029]
  Visual place recognition (VPR) is usually considered as a specific image retrieval problem. We propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features. Ours achieves state-of-the-art performance while maintaining a low computational cost.
  arXiv  Detail & Related papers  (2022-12-02T02:52:01Z)
• Joint Language Semantic and Structure Embedding for Knowledge Graph Completion [66.15933600765835]
  We propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information. Our method embeds knowledge graphs for the completion task via fine-tuning pre-trained language models. Our experiments on a variety of knowledge graph benchmarks have demonstrated the state-of-the-art performance of our method.
  arXiv  Detail & Related papers  (2022-09-19T02:41:02Z)
• Learning Statistical Texture for Semantic Segmentation [53.7443670431132]
  We propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation. For the first time, STLNet analyzes the distribution of low level information and efficiently utilizes them for the task. Based on QCO, two modules are introduced: (1) Texture Enhance Module (TEM), to capture texture-related information and enhance the texture details; (2) Pyramid Texture Feature Extraction Module (PTFEM), to effectively extract the statistical texture features from multiple scales.
  arXiv  Detail & Related papers  (2021-03-06T15:05:35Z)

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.