Learning Hybrid Image Templates (HIT) by Information Projection

By Zhangzhang Si, Song-Chun Zhu. 2012

107 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Song-Chun Zhu
2. Ying Nian Wu
3. Jianwen Xie
4. Luc Van Gool
5. Jinwoo Shin
6. Zhangzhang Si
7. Ming-Hsuan Yang
8. Alan L. Yuille

In Generative Models

1. Song-Chun Zhu
2. Ying Nian Wu
3. Jianwen Xie
4. Jinwoo Shin
5. Minsu Cho
6. Sangwoo Mo
7. Wenze Hu
8. Zhangzhang Si

Citations in the corpus

• Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs (2020, methodology): “For unconditional GANs, we fine-tune the StyleGAN [20] architecture, which is pre-trained on FFHQ [20], onto Animal Face [36] and Anime Face [30] datasets, and for conditional GANs, fine-tune the SNGAN-projection [27] architecture, which is pre-trained on ImageNet [9], onto Oxford Flower [31],…”
• Learning AND-OR Templates for Object Recognition and Detection (2013, methodology): “The proposed AOT model aims at extending our previous work—active basis template (ABT) [20] and hybrid image templates (HIT) [17].”
• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis (2021, unknown): “On 256 × 256 resolution, we test on Animal-Face Dog and Cat (Si & Zhu, 2011), 100-Shot-Obama, Panda, and Grumpy-cat (Zhao et al., 2020).”
• Learning Sparse FRAME Models for Natural Image Patterns (2014, methodology): “…published results (Si and Zhu 2012) on this dataset obtained by other methods: (a) HoG feature trained with SVM, (b) Hybrid Image Template (HIT) (Si and Zhu 2012), (c) multiple transformation invariant HITs (Mixture of HIT) (Si and Zhu 2012), and (d) part-basedHoG feature trainedwith latent SVM…”