The human language can be expressed through multiple sources of information known as modalities, including tones of voice, facial gestures, and spoken language. Recent multimodal learning with strong performances on human-centric tasks such as sentiment analysis and emotion recognition are often blackbox, with very limited interpretability. In this paper we propose Multimodal Routing, which dynamically adjusts weights between input modalities and output representations differently for each input sample. Multimodal routing can identify relative importance of both individual modalities and cross-modality features. Moreover, the weight assignment by routing allows us to interpret modalityprediction relationships not only globally (i.e. general trends over the whole dataset), but also locally for each single input sample, meanwhile keeping competitive performance compared to state-of-the-art methods. * indicates equal contribution.

No abstract

While deep learning has received a surge of interest in a variety of fields in recent years, major deep learning models barely use complex numbers. However, speech, signal and audio data are naturally complex-valued after Fourier Transform, and studies have shown a potentially richer representation of complex nets. In this paper, we propose a Complex Transformer, which incorporates the transformer model as a backbone for sequence modeling; we also develop attention and encoder-decoder network operating for complex input. The model achieves state-of-the-art performance on the MusicNet dataset and an In-phase Quadrature (IQ) signal dataset. The GitHub implementation to reproduce the experimental results is available at https://github.com/ muqiaoy/dl_signal. Index Terms-Deep learning, transformer network, sequence modeling, complex-valued deep neural network

Diabetic Retinopathy (DR) is a leading cause of blindness in working age adults. DR lesions can be challenging to identify in fundus images, and automatic DR detection systems can offer strong clinical value. Of the publicly available labeled datasets for DR, the Indian Diabetic Retinopathy Image Dataset (IDRiD) presents retinal fundus images with pixel-level annotations of four distinct lesions: microaneurysms, hemorrhages, soft exudates and hard exudates. We utilize the HEDNet edge detector to solve a semantic segmentation task on this dataset, and then propose an end-to-end system for pixel-level segmentation of DR lesions by incorporating HEDNet into a Conditional Generative Adversarial Network (cGAN). We design a loss function that adds adversarial loss to segmentation loss. Our experiments show that the addition of the adversarial loss improves the lesion segmentation performance over the baseline.

This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance. The key to the success of RPC is two-fold. First, RPC introduces the relative parameters to regularize the objective for boundedness and low variance. Second, RPC contains no logarithm and exponential score functions, which are the main cause of training instability in prior contrastive objectives. We empirically verify the effectiveness of RPC on benchmark vision and speech self-supervised learning tasks. Lastly, we relate RPC with mutual information (MI) estimation, showing RPC can be used to estimate MI with low variance 1 .