Searching a High-Performance Feature Extractor for Text Recognition Network
Feature extractor plays a critical role in text recognition (TR), but customizing its architecture is relatively less explored due to expensive manual tweaking. In this work, inspired by the success of neural architecture search (NAS), we propose to search for suitable feature extractors. We design a domain-specific search space by exploring principles for having good feature extractors. The space includes a 3D-structured space for the spatial model and a transformed-based space for the sequential model. As the space is huge and complexly structured, no existing NAS algorithms can be applied. We propose a two-stage algorithm to effectively search in the space. In the first stage, we cut the space into several blocks and progressively train each block with the help of an auxiliary head. We introduce the latency constraint into the second stage and search sub-network from the trained supernet via natural gradient descent. In experiments, a series of ablation studies are performed to better understand the designed space, search algorithm, and searched architectures. We also compare the proposed method with various state-of-the-art ones on both hand-written and scene TR tasks. Extensive results show that our approach can achieve better recognition performance with less latency.
Code (0)
등록된 구현이 없습니다.
Tasks
Neural Architecture SearchVocal Bursts Intensity PredictionSimilar Papers 제목 키워드 기반
Interrelate Training and Searching: A Unified Online Clustering Framework for Speaker Diarization
For online speaker diarization, samples arrive incrementally, and the overall distribution of the samples is invisible. Moreover, in most existing clustering-based methods, the training objective of the embedding extract…
ClusteringOnline Clusteringspeaker-diarizationSpeaker DiarizationAcoustic Word Embedding System for Code-Switching Query-by-example Spoken Term Detection
In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection. Different from previous configurations, we combine audio data i…
Word EmbeddingsTrain your classifier first: Cascade Neural Networks Training from upper layers to lower layers
Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in general, freezing the trained feature extra…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language Modellingspeech-recognition+1Neural Architecture Searching for Facial Attributes-based Depression Recognition
Recent studies show that depression can be partially reflected from human facial attributes. Since facial attributes have various data structure and carry different information, existing approaches fail to specifically c…
AttributeNeural Architecture SearchTime Series AnalysisFine-tuning a Multiple Instance Learning Feature Extractor with Masked Context Modelling and Knowledge Distillation
The first step in Multiple Instance Learning (MIL) algorithms for Whole Slide Image (WSI) classification consists of tiling the input image into smaller patches and computing their feature vectors produced by a pre-train…
Image GenerationKnowledge DistillationMultiple Instance Learning