{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dual-contradistinctive-generative-autoencoder-1","title":"Dual Contradistinctive Generative Autoencoder","arxiv_id":"2011.10063","date":"2020-11-19","proceeding":"CVPR 2021 1","authors":["Gaurav Parmar","Dacheng Li","Kwonjoon Lee","Zhuowen Tu"],"abstract":"We present a new generative autoencoder model with dual contradistinctive losses to improve generative autoencoder that performs simultaneous inference (reconstruction) and synthesis (sampling). Our model, named dual contradistinctive generative autoencoder (DC-VAE), integrates an instance-level discriminative loss (maintaining the instance-level fidelity for the reconstruction/synthesis) with a set-level adversarial loss (encouraging the set-level fidelity for there construction/synthesis), both being contradistinctive. Extensive experimental results by DC-VAE across different resolutions including 32x32, 64x64, 128x128, and 512x512 are reported. The two contradistinctive losses in VAE work harmoniously in DC-VAE leading to a significant qualitative and quantitative performance enhancement over the baseline VAEs without architectural changes. State-of-the-art or competitive results among generative autoencoders for image reconstruction, image synthesis, image interpolation, and representation learning are observed. DC-VAE is a general-purpose VAE model, applicable to a wide variety of downstream tasks in computer vision and machine learning.","url_abs":"https://arxiv.org/abs/2011.10063v1","url_pdf":"https://arxiv.org/pdf/2011.10063v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-cifar-10","task":"Image Generation","dataset":"CIFAR-10","model":"DC-VAE","rank_in_archive_order":52,"of":78,"metrics":{"FID":"17.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-128x128","task":"Image Generation","dataset":"CelebA 128x128","model":"DC-VAE","rank_in_archive_order":3,"of":5,"metrics":{"FID":"19.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-hq-256x256","task":"Image Generation","dataset":"CelebA-HQ 256x256","model":"DC-VAE","rank_in_archive_order":14,"of":19,"metrics":{"FID":"15.81"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-128-x-128","task":"Image Generation","dataset":"LSUN Bedroom 128 x 128","model":"DC-VAE","rank_in_archive_order":2,"of":2,"metrics":{"FID":"14.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-stl-10","task":"Image Generation","dataset":"STL-10","model":"DC-VAE","rank_in_archive_order":27,"of":31,"metrics":{"FID":"41.9","Inception score":"8.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.10063","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}