Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks

• URL: http://arxiv.org/abs/2006.14208v2
• Date: Tue, 6 Apr 2021 02:07:12 GMT
• Title: Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks
• Authors: Peng Zhou, Lingxi Xie, Xiaopeng Zhang, Bingbing Ni, Qi Tian
• Abstract summary: Conditional Generative Adversarial Networks (cGAN) were designed to generate images based on the provided conditions. Existing methods have used the same generating architecture for all classes. This paper presents a novel idea that adopts NAS to find a distinct architecture for each class.
• Score: 132.29772160843825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conditional Generative Adversarial Networks (cGAN) were designed to generate images based on the provided conditions, \eg, class-level distributions. However, existing methods have used the same generating architecture for all classes. This paper presents a novel idea that adopts NAS to find a distinct architecture for each class. The search space contains regular and class-modulated convolutions, where the latter is designed to introduce class-specific information while avoiding the reduction of training data for each class generator. The search algorithm follows a weight-sharing pipeline with mixed-architecture optimization so that the search cost does not grow with the number of classes. To learn the sampling policy, a Markov decision process is embedded into the search algorithm and a moving average is applied for better stability. We evaluate our approach on CIFAR10 and CIFAR100. Besides achieving better image generation quality in terms of FID scores, we discover several insights that are helpful in designing cGAN models. Code is available at https://github.com/PeterouZh/NAS_cGAN.

Related papers

• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• Improving Differentiable Architecture Search with a Generative Model [10.618008515822483]
  We introduce a training strategy called Differentiable Architecture Search with a Generative Model(DASGM)" In DASGM, the training set is used to update the classification model weight, while a synthesized dataset is used to train its architecture. The generated images have different distributions from the training set, which can help the classification model learn better features to identify its weakness.
  arXiv  Detail & Related papers  (2021-11-30T23:28:02Z)
• NAS-Bench-x11 and the Power of Learning Curves [43.4379778935488]
  We present a method using singular value decomposition and noise modeling to create surrogate benchmarks, NAS-Bench-111, NAS-Bench-311, and NAS-Bench-11. We demonstrate the power of using the full training information by introducing a learning curve extrapolation framework to modify single-fidelity algorithms.
  arXiv  Detail & Related papers  (2021-11-05T16:41:06Z)
• GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition [95.93760490301395]
  Long-tailed recognition is a problem where the number of examples per class is highly unbalanced. GistNet is proposed to support this goal, using constellations of classifier parameters to encode the class geometry. A new learning algorithm is then proposed for GeometrIc Structure Transfer (GIST), with resort to a combination of loss functions that combine class-balanced and random sampling to guarantee that, while overfitting to the popular classes is restricted to geometric parameters, it is leveraged to transfer class geometry from popular to few-shot classes.
  arXiv  Detail & Related papers  (2021-05-01T00:37:42Z)
• Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network [0.0]
  This paper describes second best submission in the competition. Our meta learning approach modifies the distribution of classes in a latent space produced by a backbone network for each class. For this task, we utilize optimal transport mapping using the Sinkhorn algorithm.
  arXiv  Detail & Related papers  (2021-02-09T23:10:58Z)
• ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding [86.40042104698792]
  We formulate neural architecture search as a sparse coding problem. In experiments, our two-stage method on CIFAR-10 requires only 0.05 GPU-day for search. Our one-stage method produces state-of-the-art performances on both CIFAR-10 and ImageNet at the cost of only evaluation time.
  arXiv  Detail & Related papers  (2020-10-13T04:34:24Z)
• NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size [31.903475598150152]
  We propose NATS-Bench, a unified benchmark on searching for both architecture topology and size. NATS-Bench includes the search space of 15,625 neural cell candidates for architecture topology and 32,768 for architecture size on three datasets.
  arXiv  Detail & Related papers  (2020-08-28T21:34:56Z)
• AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks [15.740179244963116]
  Generative Adversarial Networks (GANs) are formulated as minimax game problems, whereby generators attempt to approach real data distributions by virtue of adversarial learning against discriminators. In this work, we aim to boost model learning from the perspective of network architectures, by incorporating recent progress on automated architecture search into GANs. We propose a fully differentiable search framework for generative adversarial networks, dubbed alphaGAN.
  arXiv  Detail & Related papers  (2020-06-16T13:27:30Z)
• DC-NAS: Divide-and-Conquer Neural Architecture Search [108.57785531758076]
  We present a divide-and-conquer (DC) approach to effectively and efficiently search deep neural architectures. We achieve a $75.1%$ top-1 accuracy on the ImageNet dataset, which is higher than that of state-of-the-art methods using the same search space.
  arXiv  Detail & Related papers  (2020-05-29T09:02:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.