SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08450 · CVPR · 2022

The Devil Is in the Details: Window-based Attention for Image Compression

Zhaoxiang Zhang, Chunfeng Song, Renjie Zou

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 12 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
googolxx/stf canonical 12 of 15
FunctionStatusWhere it lives
conv Ran googolxx/stf/compressai/models/utils.py
code served (permissive licence) · get_code("f2cea3e9848ae52d")
conv1x1 Ran googolxx/stf/compressai/layers/layers.py
code served (permissive licence) · get_code("15eae621014906be")
conv3x3 Ran googolxx/stf/compressai/layers/layers.py
code served (permissive licence) · get_code("0cbeed6985b2cf30")
find_named_buffer Ran googolxx/stf/compressai/models/utils.py
code served (permissive licence) · get_code("a94389b554ddc179")
get_scale_table Ran googolxx/stf/compressai/models/cnn.py
code served (permissive licence) · get_code("feb29b32fc1ec50e")
get_scale_table Ran googolxx/stf/compressai/models/stf.py
code served (permissive licence) · get_code("1eca81f63e28f103")
ste_round Ran googolxx/stf/compressai/ops/ops.py
code served (permissive licence) · get_code("8e528b0db078ab0e")
subpel_conv3x3 Ran googolxx/stf/compressai/layers/layers.py
code served (permissive licence) · get_code("8bc3a872b71e34f4")
window_partition Ran googolxx/stf/compressai/models/stf.py
code served (permissive licence) · get_code("f6b2d702fc756d64")
window_partition Ran googolxx/stf/compressai/layers/win_attention.py
code served (permissive licence) · get_code("565f4668acf5b8f4")
window_reverse Ran googolxx/stf/compressai/layers/win_attention.py
code served (permissive licence) · get_code("fb32094c6dbece71")
window_reverse Ran googolxx/stf/compressai/models/stf.py
code served (permissive licence) · get_code("7b0d02f75bf6b439")
find_named_module Not yet run googolxx/stf/compressai/models/utils.py
code served (permissive licence) · get_code("0b4d7c9d1baaf828")
lower_bound_bwd Not yet run googolxx/stf/compressai/ops/bound_ops.py
code served (permissive licence) · get_code("07f8484bf7fe9b22")
lower_bound_fwd Not yet run googolxx/stf/compressai/ops/bound_ops.py
code served (permissive licence) · get_code("9d2139d32f9bca32")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs). Despite great contributions, a main drawback of CNN based model is that its structure is not designed for capturing local redundancy, especially the nonrepetitive textures, which severely affects the reconstruction quality. Therefore, how to make full use of both global structure and local texture becomes the core problem for learning-based image compression. Inspired by recent progresses of Vision Transformer (ViT) and Swin Transformer, we found that combining the local-aware attention mechanism with the global-related feature learning could meet the expectation in image compression. In this paper, we first extensively study the effects of multiple kinds of attention mechanisms for local features learning, then introduce a more straightforward yet effective window-based local attention block. The proposed window-based attention is very flexible which could work as a plug-and-play component to enhance CNN and Transformer models. Moreover, we propose a novel Symmetrical TransFormer (STF) framework with absolute transformer blocks in the down-sampling encoder and up-sampling decoder. Extensive experimental evaluations have shown that the proposed method is effective and outperforms the state-of-the-art methods. The code is publicly available at https://github.com/ Googolxx/STF.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.08450")
get_code_for_paper("2203.08450")
have("2203.08450")

Connect an agent — have() is free.