Skip to search formSkip to main contentSkip to account menu
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
TLDR
A hierarchical Transformer whose representation is computed with Shifted windows, which has the flexibility to model at various scales and has linear computational complexity with respect to image size and will prove beneficial for all-MLP architectures.
View on IEEE
Graph Embedding and Extensions: A General Framework for Dimensionality Reduction
TLDR
A new supervised dimensionality reduction algorithm called marginal Fisher analysis is proposed in which the intrinsic graph characterizes the intraclass compactness and connects each data point with its neighboring points of the same class, while the penalty graph connects the marginal points and characterizing the interclass separability.
View on IEEE
A High-Quality Denoising Dataset for Smartphone Cameras
TLDR
This paper proposes a systematic procedure for estimating ground truth for noisy images that can be used to benchmark denoising performance for smartphone cameras and shows that CNN-based methods perform better when trained on the authors' high-quality dataset than when trained using alternative strategies, such as low-ISO images used as a proxy for ground truth data.
View on IEEE
Deformable ConvNets V2: More Deformable, Better Results
TLDR
This work presents a reformulation of Deformable Convolutional Networks that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training, and guides network training via a proposed feature mimicking scheme that helps the network to learn features that reflect the object focus and classification power of R-CNN features.
View on IEEE
GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond
TLDR
A simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation is created, and this simplified design shares similar structure with Squeeze-Excitation Network (SENet), which generally outperforms both simplified NLNet and SENet on major benchmarks for various recognition tasks.
View on IEEE
RepPoints: Point Set Representation for Object Detection
TLDR
It is shown that an anchor-free object detector based on RepPoints can be as effective as the state-of-the-art anchor-based detection methods, with 46.5 AP and 67.4 $AP_{50}$ on the COCO test-dev detection benchmark, using ResNet-101 model.
View on IEEE
Video Swin Transformer
TLDR
This paper advocates an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization.
View PDF on arXiv
Exposure: A White-Box Photo Post-Processing Framework
TLDR
This paper presents a deep learning approach that is instead trained on unpaired data, namely a set of photographs that exhibits a retouching style the user likes, which is much easier to collect.
View PDF on arXiv
Marginal Fisher Analysis and Its Variants for Human Gait Recognition and Content- Based Image Retrieval
TLDR
Extensions of the recently proposed marginal Fisher analysis (MFA) to address dimensionality reduction problems for human gait recognition and content-based image retrieval and deal with the relevance feedback problem by extending MFA to marginal biased analysis.
View on IEEE
FC^4: Fully Convolutional Color Constancy with Confidence-Weighted Pooling
TLDR
This work presents a fully convolutional network architecture in which patches throughout an image can carry different confidence weights according to the value they provide for color constancy estimation, which allows for end-to-end training, and achieves higher efficiency and accuracy.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License