Related papers: LeMoRe: Learn More Details for Lightweight Semantic Segmentation

LeMoRe: Learn More Details for Lightweight Semantic Segmentation

URL: http://arxiv.org/abs/2505.23093v1
Date: Thu, 29 May 2025 04:55:10 GMT
Title: LeMoRe: Learn More Details for Lightweight Semantic Segmentation
Authors: Mian Muhammad Naeem Abid, Nancy Mehta, Zongwei Wu, Radu Timofte,
Abstract summary: We introduce an efficient paradigm by synergizing explicit and implicit modeling to balance computational efficiency with representational fidelity.<n>Our method combines well-defined Cartesian directions with explicitly modeled views and implicitly inferred intermediate representations, efficiently capturing global dependencies.
Score: 48.81126061219231
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Lightweight semantic segmentation is essential for many downstream vision tasks. Unfortunately, existing methods often struggle to balance efficiency and performance due to the complexity of feature modeling. Many of these existing approaches are constrained by rigid architectures and implicit representation learning, often characterized by parameter-heavy designs and a reliance on computationally intensive Vision Transformer-based frameworks. In this work, we introduce an efficient paradigm by synergizing explicit and implicit modeling to balance computational efficiency with representational fidelity. Our method combines well-defined Cartesian directions with explicitly modeled views and implicitly inferred intermediate representations, efficiently capturing global dependencies through a nested attention mechanism. Extensive experiments on challenging datasets, including ADE20K, CityScapes, Pascal Context, and COCO-Stuff, demonstrate that LeMoRe strikes an effective balance between performance and efficiency.

Related papers

Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution [88.20464308588889]
We propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR.<n>This method is designed through unfolding an SR optimization function constrained by structural similarity.<n>Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption.
arXiv Detail & Related papers (2025-06-13T14:29:40Z)
Platonic Grounding for Efficient Multimodal Language Models [22.715168904364756]
We motivate and propose a simple modification to existing multimodal frameworks that rely on aligning pretrained models.<n>Our work also has implications for combining pretrained models into larger systems efficiently.
arXiv Detail & Related papers (2025-04-27T18:56:26Z)
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
arXiv Detail & Related papers (2025-02-18T02:37:26Z)
ContextFormer: Redefining Efficiency in Semantic Segmentation [48.81126061219231]
Convolutional methods, although capturing local dependencies well, struggle with long-range relationships.<n>Vision Transformers (ViTs) excel in global context capture but are hindered by high computational demands.<n>We propose ContextFormer, a hybrid framework leveraging the strengths of CNNs and ViTs in the bottleneck to balance efficiency, accuracy, and robustness for real-time semantic segmentation.
arXiv Detail & Related papers (2025-01-31T16:11:04Z)
Learning Free Token Reduction for Multi-Modal Large Language Models [3.4026156483879517]
Vision-Language Models (VLMs) have achieved remarkable success across a range of multimodal tasks.<n>However, their practical deployment is often constrained by high computational costs and prolonged inference times.<n>We propose a token compression paradigm that operates on both spatial and temporal dimensions.
arXiv Detail & Related papers (2025-01-29T02:52:32Z)
Contextual Reinforcement in Multimodal Token Compression for Large Language Models [0.0]
token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets.<n>A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance through interdependencies and semantic relevance.<n>This approach enables substantial reductions in token usage while preserving the quality and coherence of information representation.
arXiv Detail & Related papers (2025-01-28T02:44:31Z)
Latent Variable Representation for Reinforcement Learning [131.03944557979725]
It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
arXiv Detail & Related papers (2022-12-17T00:26:31Z)
SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision [54.16430358203348]
We propose a simple but effective slimmable semantic segmentation (SlimSeg) method, which can be executed at different capacities during inference. We show that our proposed SlimSeg with various mainstream networks can produce flexible models that provide dynamic adjustment of computational cost and better performance.
arXiv Detail & Related papers (2022-07-13T14:41:05Z)

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