FSNet detects unknown invisible watermarks via adaptive frequency gating and multi-spectral attention on the UniFreq-100K dataset, claiming superior zero-shot performance.
Swin transformer: Hierarchical vision transformer using shifted windows
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 6roles
background 1polarities
background 1representative citing papers
Canonical logit- and feature-based knowledge distillation outperform complex segmentation-specific methods under matched wall-clock compute and achieve near-teacher performance with extended training on Cityscapes and ADE20K.
HyperFM is a new efficient hyperspectral foundation model using spectral grouping and hybrid attention that shows performance gains on cloud property retrieval tasks from PACE data, accompanied by the release of the HyperFM250K dataset.
UCAN unifies window-based spatial attention and Hedgehog Attention with a distillation-based large-kernel module and cross-layer sharing to deliver competitive PSNR at low MACs in lightweight super-resolution.
GAIR introduces a geo-aligned implicit representation module inside a multi-encoder contrastive SSL framework that produces location-aware embeddings and outperforms prior geo-foundation models on 22 geospatial datasets across 9 tasks.
ETCTrack compresses template tokens by 60% in visual trackers via an adaptive compressor and hierarchical interaction, cutting MACs 21.4% with 0.4% accuracy drop on seven benchmarks.
citing papers explorer
-
AWPD: Frequency Shield Network for Agnostic Watermark Presence Detection
FSNet detects unknown invisible watermarks via adaptive frequency gating and multi-spectral attention on the UniFreq-100K dataset, claiming superior zero-shot performance.
-
The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation
Canonical logit- and feature-based knowledge distillation outperform complex segmentation-specific methods under matched wall-clock compute and achieve near-teacher performance with extended training on Cityscapes and ADE20K.
-
HyperFM: An Efficient Hyperspectral Foundation Model with Spectral Grouping
HyperFM is a new efficient hyperspectral foundation model using spectral grouping and hybrid attention that shows performance gains on cloud property retrieval tasks from PACE data, accompanied by the release of the HyperFM250K dataset.
-
UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution
UCAN unifies window-based spatial attention and Hedgehog Attention with a distillation-based large-kernel module and cross-layer sharing to deliver competitive PSNR at low MACs in lightweight super-resolution.
-
GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representations
GAIR introduces a geo-aligned implicit representation module inside a multi-encoder contrastive SSL framework that produces location-aware embeddings and outperforms prior geo-foundation models on 22 geospatial datasets across 9 tasks.
-
An Efficient Token Compression Framework for Visual Object Tracking
ETCTrack compresses template tokens by 60% in visual trackers via an adaptive compressor and hierarchical interaction, cutting MACs 21.4% with 0.4% accuracy drop on seven benchmarks.