Entroformer: A Transformer-based Entropy Model for Learned Image Compression
This work addresses a bottleneck in deep image compression for applications requiring high-quality encoding, though it is incremental as it builds on existing transformer architectures.
The paper tackles the problem of capturing global dependencies in entropy models for learned image compression by proposing Entroformer, a transformer-based entropy model with optimized attention and position encoding, achieving state-of-the-art performance with time efficiency.
One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon convolutional neural networks which are inefficient in capturing global dependencies. In this work, we propose a novel transformer-based entropy model, termed Entroformer, to capture long-range dependencies in probability distribution estimation effectively and efficiently. Different from vision transformers in image classification, the Entroformer is highly optimized for image compression, including a top-k self-attention and a diamond relative position encoding. Meanwhile, we further expand this architecture with a parallel bidirectional context model to speed up the decoding process. The experiments show that the Entroformer achieves state-of-the-art performance on image compression while being time-efficient.