Dynamic Multimodal Information Bottleneck for Multimodality Classification

Effectively leveraging multimodal data such as various images, laboratory tests and clinical information is gaining traction in a variety of AI-based medical diagnosis and prognosis tasks. Most existing multi-modal techniques only focus on enhancing their performance by leveraging the differences or shared features from various modalities and fusing feature across different modalities. These approaches are generally not optimal for clinical settings, which pose the additional challenges of limited training data, as well as being rife with redundant data or noisy modality channels, leading to subpar performance. To address this gap, we study the robustness of existing methods to data redundancy and noise and propose a generalized dynamic multimodal information bottleneck framework for attaining a robust fused feature representation. Specifically, our information bottleneck module serves to filter out the task-irrelevant information and noises in the fused feature, and we further introduce a sufficiency loss to prevent dropping of task-relevant information, thus explicitly preserving the sufficiency of prediction information in the distilled feature. We validate our model on an in-house and a public COVID19 dataset for mortality prediction as well as two public biomedical datasets for diagnostic tasks. Extensive experiments show that our method surpasses the state-of-the-art and is significantly more robust, being the only method to remain performance when large-scale noisy channels exist. Our code is publicly available at https://github.com/BII-wushuang/DMIB.

VDIP-TGV: Blind Image Deconvolution via Variational Deep Image Prior Empowered by Total Generalized Variation

Recovering clear images from blurry ones with an unknown blur kernel is a challenging problem. Deep image prior (DIP) proposes to use the deep network as a regularizer for a single image rather than as a supervised model, which achieves encouraging results in the nonblind deblurring problem. However, since the relationship between images and the network architectures is unclear, it is hard to find a suitable architecture to provide sufficient constraints on the estimated blur kernels and clean images. Also, DIP uses the sparse maximum a posteriori (MAP), which is insufficient to enforce the selection of the recovery image. Recently, variational deep image prior (VDIP) was proposed to impose constraints on both blur kernels and recovery images and take the standard deviation of the image into account during the optimization process by the variational principle. However, we empirically find that VDIP struggles with processing image details and tends to generate suboptimal results when the blur kernel is large. Therefore, we combine total generalized variational (TGV) regularization with VDIP in this paper to overcome these shortcomings of VDIP. TGV is a flexible regularization that utilizes the characteristics of partial derivatives of varying orders to regularize images at different scales, reducing oil painting artifacts while maintaining sharp edges. The proposed VDIP-TGV effectively recovers image edges and details by supplementing extra gradient information through TGV. Additionally, this model is solved by the alternating direction method of multipliers (ADMM), which effectively combines traditional algorithms and deep learning methods. Experiments show that our proposed VDIP-TGV surpasses various state-of-the-art models quantitatively and qualitatively.

EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services are released for generating high-visual quality videos. However, these methods often use a few academic metrics, for example, FVD or IS, to evaluate the performance. We argue that it is hard to judge the large conditional generative models from the simple metrics since these models are often trained on very large datasets with multi-aspect abilities. Thus, we propose a new framework and pipeline to exhaustively evaluate the performance of the generated videos. To achieve this, we first conduct a new prompt list for text-to-video generation by analyzing the real-world prompt list with the help of the large language model. Then, we evaluate the state-of-the-art video generative models on our carefully designed benchmarks, in terms of visual qualities, content qualities, motion qualities, and text-caption alignment with around 18 objective metrics. To obtain the final leaderboard of the models, we also fit a series of coefficients to align the objective metrics to the users' opinions. Based on the proposed opinion alignment method, our final score shows a higher correlation than simply averaging the metrics, showing the effectiveness of the proposed evaluation method.

DSFNet: Convolutional Encoder-Decoder Architecture Combined Dual-GCN and Stand-alone Self-attention by Fast Normalized Fusion for Polyps Segmentation

In the past few decades, deep learning technology has been widely used in medical image segmentation and has made significant breakthroughs in the fields of liver and liver tumor segmentation, brain and brain tumor segmentation, video disc segmentation, heart image segmentation, and so on. However, the segmentation of polyps is still a challenging task since the surface of the polyps is flat and the color is very similar to that of surrounding tissues. Thus, It leads to the problems of the unclear boundary between polyps and surrounding mucosa, local overexposure, and bright spot reflection. To counter this problem, this paper presents a novel U-shaped network, namely DSFNet, which effectively combines the advantages of Dual-GCN and self-attention mechanisms. First, we introduce a feature enhancement block module based on Dual-GCN module as an attention mechanism to enhance the feature extraction of local spatial and structural information with fine granularity. Second, the stand-alone self-attention module is designed to enhance the integration ability of the decoding stage model to global information. Finally, the Fast Normalized Fusion method with trainable weights is used to efficiently fuse the corresponding three feature graphs in encoding, bottleneck, and decoding blocks, thus promoting information transmission and reducing the semantic gap between encoder and decoder. Our model is tested on two public datasets including Endoscene and Kvasir-SEG and compared with other state-of-the-art models. Experimental results show that the proposed model surpasses other competitors in many indicators, such as Dice, MAE, and IoU. In the meantime, ablation studies are also conducted to verify the efficacy and effectiveness of each module. Qualitative and quantitative analysis indicates that the proposed model has great clinical significance.

BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration

Deep learning has achieved remarkable success in the field of bearing fault diagnosis. However, this success comes with larger models and more complex computations, which cannot be transferred into industrial fields requiring models to be of high speed, strong portability, and low power consumption. In this paper, we propose a lightweight and deployable model for bearing fault diagnosis, referred to as BearingPGA-Net, to address these challenges. Firstly, aided by a well-trained large model, we train BearingPGA-Net via decoupled knowledge distillation. Despite its small size, our model demonstrates excellent fault diagnosis performance compared to other lightweight state-of-the-art methods. Secondly, we design an FPGA acceleration scheme for BearingPGA-Net using Verilog. This scheme involves the customized quantization and designing programmable logic gates for each layer of BearingPGA-Net on the FPGA, with an emphasis on parallel computing and module reuse to enhance the computational speed. To the best of our knowledge, this is the first instance of deploying a CNN-based bearing fault diagnosis model on an FPGA. Experimental results reveal that our deployment scheme achieves over 200 times faster diagnosis speed compared to CPU, while achieving a lower-than-0.4\% performance drop in terms of F1, Recall, and Precision score on our independently-collected bearing dataset. Our code is available at \url{https://github.com/asdvfghg/BearingPGA-Net}.

Deep ReLU Networks Have Surprisingly Simple Polytopes

A ReLU network is a piecewise linear function over polytopes. Figuring out the properties of such polytopes is of fundamental importance for the research and development of neural networks. So far, either theoretical or empirical studies on polytopes only stay at the level of counting their number, which is far from a complete characterization of polytopes. To upgrade the characterization to a new level, here we propose to study the shapes of polytopes via the number of simplices obtained by triangulating the polytope. Then, by computing and analyzing the histogram of simplices across polytopes, we find that a ReLU network has relatively simple polytopes under both initialization and gradient descent, although these polytopes theoretically can be rather diverse and complicated. This finding can be appreciated as a novel implicit bias. Next, we use nontrivial combinatorial derivation to theoretically explain why adding depth does not create a more complicated polytope by bounding the average number of faces of polytopes with a function of the dimensionality. Our results concretely reveal what kind of simple functions a network learns and its space partition property. Also, by characterizing the shape of polytopes, the number of simplices be a leverage for other problems, \textit{e.g.}, serving as a generic functional complexity measure to explain the power of popular shortcut networks such as ResNet and analyzing the impact of different regularization strategies on a network's space partition.

Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance

The networks for point cloud tasks are expected to be invariant when the point clouds are affinely transformed such as rotation and reflection. So far, relative to the rotational invariance that has been attracting major research attention in the past years, the reflection invariance is little addressed. Notwithstanding, reflection symmetry can find itself in very common and important scenarios, e.g., static reflection symmetry of structured streets, dynamic reflection symmetry from bidirectional motion of moving objects (such as pedestrians), and left- and right-hand traffic practices in different countries. To the best of our knowledge, unfortunately, no reflection-invariant network has been reported in point cloud analysis till now. To fill this gap, we propose a framework by using quadratic neurons and PCA canonical representation, referred to as Cloud-RAIN, to endow point \underline{Cloud} models with \underline{R}eflection\underline{A}l \underline{IN}variance. We prove a theorem to explain why Cloud-RAIN can enjoy reflection symmetry. Furthermore, extensive experiments also corroborate the reflection property of the proposed Cloud-RAIN and show that Cloud-RAIN is superior to data augmentation. Our code is available at https://github.com/YimingCuiCuiCui/Cloud-RAIN.

Rethink Depth Separation with Intra-layer Links

The depth separation theory is nowadays widely accepted as an effective explanation for the power of depth, which consists of two parts: i) there exists a function representable by a deep network; ii) such a function cannot be represented by a shallow network whose width is lower than a threshold. However, this theory is established for feedforward networks. Few studies, if not none, considered the depth separation theory in the context of shortcuts which are the most common network types in solving real-world problems. Here, we find that adding intra-layer links can modify the depth separation theory. First, we report that adding intra-layer links can greatly improve a network's representation capability through bound estimation, explicit construction, and functional space analysis. Then, we modify the depth separation theory by showing that a shallow network with intra-layer links does not need to go as wide as before to express some hard functions constructed by a deep network. Such functions include the renowned "sawtooth" functions. Moreover, the saving of width is up to linear. Our results supplement the existing depth separation theory by examining its limit in the shortcut domain. Also, the mechanism we identify can be translated into analyzing the expressivity of popular shortcut networks such as ResNet and DenseNet, \textit{e.g.}, residual connections empower a network to represent a sawtooth function efficiently.

Recognizable Information Bottleneck

Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalization in real-world scenarios due to the vacuous generalization bound. The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound. However, it requires the computation of expensive second-order curvature, which hinders its practical application. In this paper, we establish the connection between the recognizability of representations and the recent functional conditional mutual information (f-CMI) generalization bound, which is significantly easier to estimate. On this basis we propose a Recognizable Information Bottleneck (RIB) which regularizes the recognizability of representations through a recognizability critic optimized by density ratio matching under the Bregman divergence. Extensive experiments on several commonly used datasets demonstrate the effectiveness of the proposed method in regularizing the model and estimating the generalization gap.