The local and global features are both essential for automatic speech
recognition (ASR). Many recent methods have verified that simply combining
local and global features can further promote ASR performance. However, these
methods pay less attention to the interaction of local and global features, and
their series architectures are rigid to reflect local and global relationships.
To address these issues, this paper proposes InterFormer for interactive local
and global features fusion to learn a better representation for ASR.
Specifically, we combine the convolution block with the transformer block in a
parallel design. Besides, we propose a bidirectional feature interaction module
(BFIM) and a selective fusion module (SFM) to implement the interaction and
fusion of local and global features, respectively. Extensive experiments on
public ASR datasets demonstrate the effectiveness of our proposed InterFormer
and its superior performance over the other Transformer and Conformer models.

本文提出 InterFormer 方法，使用双向特征交互模块和选择性融合模块实现局部和全局特征的交互和融合，应用于自动语音识别领域，取得比 Transformer 和 Conformer 更好的性能表现。

InterFormer：自动语音识别的交互式局部和全局特征融合

InterFormer: Interactive Local and Global Features Fusion for Automatic  Speech Recognition

Interactive image segmentation enables annotators to efficiently perform
pixel-level annotation for segmentation tasks. However, the existing
interactive segmentation pipeline suffers from inefficient computations of
interactive models because of the following two issues. First, annotators'
later click is based on models' feedback of annotators' former click. This
serial interaction is unable to utilize model's parallelism capabilities.
Second, the model has to repeatedly process the image, the annotator's current
click, and the model's feedback of the annotator's former clicks at each step
of interaction, resulting in redundant computations. For efficient computation,
we propose a method named InterFormer that follows a new pipeline to address
these issues. InterFormer extracts and preprocesses the computationally
time-consuming part i.e. image processing from the existing process.
Specifically, InterFormer employs a large vision transformer (ViT) on
high-performance devices to preprocess images in parallel, and then uses a
lightweight module called interactive multi-head self attention (I-MSA) for
interactive segmentation. Furthermore, the I-MSA module's deployment on
low-power devices extends the practical application of interactive
segmentation. The I-MSA module utilizes the preprocessed features to
efficiently response to the annotator inputs in real-time. The experiments on
several datasets demonstrate the effectiveness of InterFormer, which
outperforms previous interactive segmentation models in terms of computational
efficiency and segmentation quality, achieve real-time high-quality interactive
segmentation on CPU-only devices.

提出了一种名为 InterFormer 的方法，使用大型 ViT 并在高性能设备上运行，通过轻量级 I-MSA 模块进行互动式分割，实现了计算效率更高、分割质量更好的实时高质量交互式分割，可在仅有 CPU 的设备上执行。

InterFormer：实时交互式图像分割

InterFormer: Real-time Interactive Image Segmentation

Recently, Flat-LAttice Transformer (FLAT) has achieved great success in
Chinese Named Entity Recognition (NER). FLAT performs lexical enhancement by
constructing flat lattices, which mitigates the difficulties posed by blurred
word boundaries and the lack of word semantics. In FLAT, the positions of
starting and ending characters are used to connect a matching word. However,
this method is likely to match more words when dealing with long texts,
resulting in long input sequences. Therefore, it significantly increases the
memory and computational costs of the self-attention module. To deal with this
issue, we advocate a novel lexical enhancement method, InterFormer, that
effectively reduces the amount of computational and memory costs by
constructing non-flat lattices. Furthermore, with InterFormer as the backbone,
we implement NFLAT for Chinese NER. NFLAT decouples lexicon fusion and context
feature encoding. Compared with FLAT, it reduces unnecessary attention
calculations in "word-character" and "word-word". This reduces the memory usage
by about 50% and can use more extensive lexicons or higher batches for network
training. The experimental results obtained on several well-known benchmarks
demonstrate the superiority of the proposed method over the state-of-the-art
hybrid (character-word) models.

本文提出一种新的词汇增强方法 InterFormer，可以有效地减少计算和内存成本。我们以 InterFormer 为主干实现 NFLAT 来进行中文命名实体识别，其解耦了词汇融合和上下文特征编码，使得内存使用减少约 50％。在多个著名基准测试中，我们通过与字符 - 词混合模型等现有模型的比较表明，该方法优于所有模型。