AtomNAS: Fine-Grained End-to-End Neural Architecture Search
This work addresses the challenge of automating neural network design for computer vision tasks, offering a more efficient and flexible approach compared to previous methods.
The paper tackles the problem of designing efficient neural architectures by proposing AtomNAS, a fine-grained neural architecture search method that uses atomic blocks to allow heterogeneous operations and jointly optimizes performance and computational cost. It achieves state-of-the-art results on ImageNet under various FLOPs constraints with reduced search time.
Search space design is very critical to neural architecture search (NAS) algorithms. We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that is much smaller than the ones used in recent NAS algorithms. This search space allows a mix of operations by composing different types of atomic blocks, while the search space in previous methods only allows homogeneous operations. Based on this search space, we propose a resource-aware architecture search framework which automatically assigns the computational resources (e.g., output channel numbers) for each operation by jointly considering the performance and the computational cost. In addition, to accelerate the search process, we propose a dynamic network shrinkage technique which prunes the atomic blocks with negligible influence on outputs on the fly. Instead of a search-and-retrain two-stage paradigm, our method simultaneously searches and trains the target architecture. Our method achieves state-of-the-art performance under several FLOPs configurations on ImageNet with a small searching cost. We open our entire codebase at: https://github.com/meijieru/AtomNAS.