Methods › General › Loss Functions › VGG Loss

VGG Loss

37 papers tagged archive 2025-07-28

Introduced by Christian Ledig et al. in Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

VGG Loss is a type of content loss introduced in the Perceptual Losses for Real-Time Style Transfer and Super-Resolution super-resolution and style transfer framework. It is an alternative to pixel-wise losses; VGG Loss attempts to be closer to perceptual similarity. The VGG loss is based on the ReLU activation layers of the pre-trained 19 layer VGG network. With ϕ_(i,j) we indicate the feature map obtained by the j-th convolution (after activation) before the i-th maxpooling layer within the VGG19 network, which we consider given. We then define the VGG loss as the euclidean distance between the feature representations of a reconstructed image G_(θ_G)(Iᴸᴿ) and the reference image Iᴴᴿ:

l_(VGG/i.j) = 1/(W_(i,j)H_(i,j))∑ₓ₌₁^(W_(i,j))∑_(y=1)^(H_(i,j))(ϕ_(i,j)(Iᴴᴿ)_(x, y) - ϕ_(i,j)(G_(θ_G)(Iᴸᴿ))_(x, y))²

Here W_(i,j) and H_(i,j) describe the dimensions of the respective feature maps within the VGG network.

PaperSourceSee Code · tensorlayer/srgan

Papers archive 2025-07-28

30 shown of 37, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 41 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Super-Resolution34
Image Super-Resolution23
Generative Adversarial Network14
SSIM8
Quantization2
Video Super-Resolution2
Brain Tumor Segmentation1
CPU1
Data Compression1
Deep Learning1
Denoising1
Diversity1
Domain Adaptation1
Edge Detection1
Face Hallucination1
GPU1
Image Classification1
Image Compression1
Image Enhancement1
Image Generation1

Usage over time archive 2025-07-28

Papers per year tagged with VGG Loss: 2016 to 2025, peak 9 9 0 2016: 1 paper 2016 2017: 0 papers 2017 2018: 6 papers 2018 2019: 6 papers 2019 2020: 9 papers 2020 2021: 3 papers 2021 2022: 4 papers 2022 2023: 3 papers 2023 2024: 4 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (37 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Loss Functions

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections