Behavior of neural networks is irremediably determined by the specific loss
and data used during training. However it is often desirable to tune the model
at inference time based on external factors such as preferences of the user or
dynamic characteristics of the data. This is especially important to balance
the perception-distortion trade-off of ill-posed image-to-image translation
tasks. In this work, we propose to optimize a parametric tunable convolutional
layer, which includes a number of different kernels, using a parametric
multi-loss, which includes an equal number of objectives. Our key insight is to
use a shared set of parameters to dynamically interpolate both the objectives
and the kernels. During training, these parameters are sampled at random to
explicitly optimize all possible combinations of objectives and consequently
disentangle their effect into the corresponding kernels. During inference,
these parameters become interactive inputs of the model hence enabling reliable
and consistent control over the model behavior. Extensive experimental results
demonstrate that our tunable convolutions effectively work as a drop-in
replacement for traditional convolutions in existing neural networks at
virtually no extra computational cost, outperforming state-of-the-art control
strategies in a wide range of applications; including image denoising,
deblurring, super-resolution, and style transfer.

本文提出了一种使用参数可调卷积层进行对象和卷积核动态插值优化的方法，能够在不增加额外计算代价的前提下，有效地替代传统卷积，并在图像去噪、去模糊、超分辨率和风格转移等应用中表现优异。

可调卷积与参数多损失优化

Tunable Convolutions with Parametric Multi-Loss Optimization

Recently, Conformer based CTC/AED model has become a mainstream architecture
for ASR. In this paper, based on our prior work, we identify and integrate
several approaches to achieve further improvements for ASR tasks, which we
denote as multi-loss, multi-path and multi-level, summarized as "3M" model.
Specifically, multi-loss refers to the joint CTC/AED loss and multi-path
denotes the Mixture-of-Experts(MoE) architecture which can effectively increase
the model capacity without remarkably increasing computation cost. Multi-level
means that we introduce auxiliary loss at multiple level of a deep model to
help training. We evaluate our proposed method on the public WenetSpeech
dataset and experimental results show that the proposed method provides
12.2%-17.6% relative CER improvement over the baseline model trained by Wenet
toolkit. On our large scale dataset of 150k hours corpus, the 3M model has also
shown obvious superiority over the baseline Conformer model. Code is publicly
available at this https URL.

本论文提出 3M 模型，即多重损失、多重路径和多重水平，作为 ASR 任务中 CTC/AED 模型的改进措施，并在公共数据集和大规模数据集方面表现出明显的优越性。

3M：语音识别的多损失、多路径和多层级神经网络

3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition

Existing person re-identification (re-id) methods rely mostly on either
localised or global feature representation alone. This ignores their joint
benefit and mutual complementary effects. In this work, we show the advantages
of jointly learning local and global features in a Convolutional Neural Network
(CNN) by aiming to discover correlated local and global features in different
context. Specifically, we formulate a method for joint learning of local and
global feature selection losses designed to optimise person re-id when using
only generic matching metrics such as the L2 distance. We design a novel CNN
architecture for Jointly Learning Multi-Loss (JLML) of local and global
discriminative feature optimisation subject concurrently to the same re-id
labelled information. Extensive comparative evaluations demonstrate the
advantages of this new JLML model for person re-id over a wide range of
state-of-the-art re-id methods on five benchmarks (VIPeR, GRID, CUHK01, CUHK03,
Market-1501).

本文提出了一种使用 CNN 联合学习局部和全局特征的方法，用于重新识别目标，实现了对多任务的优化，通过优化多任务的联合损失函数，达到一种损失函数的平衡，该模型在 VIPeR、GRID、CUHK01、CUHK03 和 Market-1501 的五个基准测试中优于现有的各种重新识别方法。