cs.CVNov 7, 2026

FG-DSA: Frequency-Guided Depthwise Separable Attention for Efficient Dense Prediction

Authors: Yiyao Yang

Organizations: Nanyang Technological University, Singapore

Abstract

Dense prediction and generative modeling in resource-constrained scenarios remain challenging, as repeated downsampling substantially reduces spatial detail and degrades boundaries. Although recent attention mechanisms have alleviated the problem of semantic ambiguity, they often fail to preserve high-frequency features or do so at the expense of a very high computational cost. In this paper, we propose the Frequency Guided Depthwise Separable Attention for Efficient Dense Prediction (FG-DSA), a novel framework for efficient dense visual understanding and generation. FG-DSA employs a 2D FFT high-pass filtering module to explicitly inject frequency domain priors into the spatial attention mechanism, allowing lightweight networks to recover sharp boundary transitions with linear complexity. A range of experiments show that FG-DSA is effective at recovering fine object boundaries and leads to a consistent performance gain in the task of semantic segmentation. Importantly, we show that FGA-DSA can be used as a module in diffusion-based generative U-Nets, leading to a significant improvement in the detail of the generated images with very little additional parameter and Floating Point Operation (FLOP) cost.

Explore similar work

Oct 26, 2026

FGD2HF: Frequency-guided Dual-domain Hypergraph Fusion for Semantic Segmentation

Frequency-domain information is beneficial for semantic segmentation. However, existing frequency-based methods often suffer from insufficient frequency utilization, inefficient fusion, and high computational complexity. To address these issues, we propose FGD2HF, a dual-domain fusion network that leverages frequency features to guide spatial-domain fusion and enhancement. Specifically, we introduce a novel Hybrid-Attention Encoder (NAHA) that jointly models local and global relationships through neighborhood and hypergraph attention, enhancing the network's ability to extract effective features. We further introduce a Wavelet Transform and Enhancement (WTE) module to extract and refine low- and high-frequency cues from preceding-stage features, followed by Frequency-guided Dual-domain Fusion (FGDF) modules that use frequency cues to condition current-stage spatial grouping and feature propagation. This design incorporates both global and local frequency guidance into spatial feature modulation, enhancement and fusion with low computational cost. Extensive comparisons with numerous state-of-the-art semantic segmentation methods demonstrate that our method is highly competitive. Our full FGD2HF-B model achieves 48.7% mIoU on ADE20K (+0.3% over SegMAN-B with 18% fewer GFLOPs), 83.2% mIoU on Cityscapes (comparable to SegMAN-B with 21% fewer GFLOPs), and 1.1% higher mIoU than VWFormer-T on SBD with 21% fewer GFLOPs, while also achieving significant improvements in boundary segmentation accuracy.
Aug 31, 2026

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention

This work presents Lapis\textbf{Lapis}, a l\textbf{l}inear-a\textbf{a}ttention-based pi\textbf{pi}xel-s\textbf{s}pace generative framework that achieves efficient and high-fidelity depth estimation with one-step diffusion. While generative frameworks have significantly advanced monocular depth estimation with superior detail fidelity, the O(N2)\mathcal{O}(N^2) complexity of standard attention and the multi-step denoising process introduce prohibitive computational costs when scaling them to high-resolution image applications. Although linear attention and one-step prediction are intuitively viable, directly applying them leads to poor structural consistency, detail loss, and noise. Lapis rectifies these limitations through a coarse-to-fine hierarchy. Specifically, a Patch-level Consistency Module restores structural coherence by integrating semantic and spatial priors. Subsequently, a Pixel-level Refinement Module recovers sharp geometric boundaries via skip-connection-based pixel correspondence. Furthermore, to mitigate sampling noise inherent in one-step diffusion, we leverage the manifold assumption and adopt a direct x\mathbf{x}-prediction strategy to target the clean data manifold. Extensive evaluations on multiple benchmarks demonstrate that Lapis consistently achieves state-of-the-art (SOTA) accuracy and boundary sharpness across various resolutions, reducing inference latency by up to 7.6×\times at 1080P and 10.9×\times at 1440P resolution compared to previous SOTA generative models.
May 21, 2026

SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by modifying inference-time attention behavior, often through Rotary Position Embeddings (RoPE) extrapolation combined with attention scaling. However, these strategies apply a uniform and content-agnostic scaling across RoPE components with distinct frequency characteristics, inducing a trade-off between preserving global structure and recovering fine detail. We introduce SEGA, a training-free method that dynamically scales attention across RoPE components according to the latent's spatial-frequency structure at each denoising step. This adaptive scaling improves both structural coherence and fine-detail fidelity. Experiments show that SEGA consistently improves high-resolution synthesis across multiple target resolutions, outperforming state-of-the-art training-free baselines.