Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

Automatic font generation without human experts is a practical and significant problem, especially for some languages that consist of a large number of characters. Existing methods for font generation are often in supervised learning. They require a large number of paired data, which are labor-intensive and expensive to collect. In contrast, common unsupervised image-to-image translation methods are not applicable to font generation, as they often define style as the set of textures and colors. In this work, we propose a robust deformable generative network for unsupervised font generation (abbreviated as DGFont++). We introduce a feature deformation skip connection (FDSC) to learn local patterns and geometric transformations between fonts. The FDSC predicts pairs of displacement maps and employs the predicted maps to apply deformable convolution to the low-level content feature maps. The outputs of FDSC are fed into a mixer to generate final results. Moreover, we introduce contrastive self-supervised learning to learn a robust style representation for fonts by understanding the similarity and dissimilarities of fonts. To distinguish different styles, we train our model with a multi-task discriminator, which ensures that each style can be discriminated independently. In addition to adversarial loss, another two reconstruction losses are adopted to constrain the domain-invariant characteristics between generated images and content images. Taking advantage of FDSC and the adopted loss functions, our model is able to maintain spatial information and generates high-quality character images in an unsupervised manner. Experiments demonstrate that our model is able to generate character images of higher quality than state-of-the-art methods.

Normalizing flow is a class of deep generative models for efficient sampling and density estimation. In practice, the flow often appears as a chain of invertible neural network blocks; to facilitate training, existing works have regularized flow trajectories and designed special network architectures. The current paper develops a neural ODE flow network inspired by the Jordan-Kinderleherer-Otto (JKO) scheme, which allows efficient block-wise training of the residual blocks and avoids inner loops of score matching or variational learning. As the JKO scheme unfolds the dynamic of gradient flow, the proposed model naturally stacks residual network blocks one-by-one, reducing the memory load and difficulty of performing end-to-end training of deep flow networks. We also develop adaptive time reparameterization of the flow network with a progressive refinement of the trajectory in probability space, which improves the model training efficiency and accuracy in practice. Using numerical experiments with synthetic and real data, we show that the proposed JKO-iFlow model achieves similar or better performance in generating new samples compared with existing flow and diffusion models at a significantly reduced computational and memory cost.

This paper introduces a learned hierarchical B-frame coding scheme in response to the Grand Challenge on Neural Network-based Video Coding at ISCAS 2023. We address specifically three issues, including (1) B-frame coding, (2) YUV 4:2:0 coding, and (3) content-adaptive variable-rate coding with only one single model. Most learned video codecs operate internally in the RGB domain for P-frame coding. B-frame coding for YUV 4:2:0 content is largely under-explored. In addition, while there have been prior works on variable-rate coding with conditional convolution, most of them fail to consider the content information. We build our scheme on conditional augmented normalized flows (CANF). It features conditional motion and inter-frame codecs for efficient B-frame coding. To cope with YUV 4:2:0 content, two conditional inter-frame codecs are used to process the Y and UV components separately, with the coding of the UV components conditioned additionally on the Y component. Moreover, we introduce adaptive feature modulation in every convolutional layer, taking into account both the content information and the coding levels of B-frames to achieve content-adaptive variable-rate coding. Experimental results show that our model outperforms x265 and the winner of last year's challenge on commonly used datasets in terms of PSNR-YUV.

Gradient-based explanation is the cornerstone of explainable deep networks, but it has been shown to be vulnerable to adversarial attacks. However, existing works measure the explanation robustness based on $\ell_p$-norm, which can be counter-intuitive to humans, who only pay attention to the top few salient features. We propose explanation ranking thickness as a more suitable explanation robustness metric. We then present a new practical adversarial attacking goal for manipulating explanation rankings. To mitigate the ranking-based attacks while maintaining computational feasibility, we derive surrogate bounds of the thickness that involve expensive sampling and integration. We use a multi-objective approach to analyze the convergence of a gradient-based attack to confirm that the explanation robustness can be measured by the thickness metric. We conduct experiments on various network architectures and diverse datasets to prove the superiority of the proposed methods, while the widely accepted Hessian-based curvature smoothing approaches are not as robust as our method.

Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense. Among these methods, adversarial training has been drawing increasing attention because of its simplicity and effectiveness. However, the performance of the adversarial training is greatly limited by the architectures of target DNNs, which often makes the resulting DNNs with poor accuracy and unsatisfactory robustness. To address this problem, we propose DSARA to automatically search for the neural architectures that are accurate and robust after adversarial training. In particular, we design a novel cell-based search space specially for adversarial training, which improves the accuracy and the robustness upper bound of the searched architectures by carefully designing the placement of the cells and the proportional relationship of the filter numbers. Then we propose a two-stage search strategy to search for both accurate and robust neural architectures. At the first stage, the architecture parameters are optimized to minimize the adversarial loss, which makes full use of the effectiveness of the adversarial training in enhancing the robustness. At the second stage, the architecture parameters are optimized to minimize both the natural loss and the adversarial loss utilizing the proposed multi-objective adversarial training method, so that the searched neural architectures are both accurate and robust. We evaluate the proposed algorithm under natural data and various adversarial attacks, which reveals the superiority of the proposed method in terms of both accurate and robust architectures. We also conclude that accurate and robust neural architectures tend to deploy very different structures near the input and the output, which has great practical significance on both hand-crafting and automatically designing of accurate and robust neural architectures.

Audio-visual approaches involving visual inputs have laid the foundation for recent progress in speech separation. However, the optimization of the concurrent usage of auditory and visual inputs is still an active research area. Inspired by the cortico-thalamo-cortical circuit, in which the sensory processing mechanisms of different modalities modulate one another via the non-lemniscal sensory thalamus, we propose a novel cortico-thalamo-cortical neural network (CTCNet) for audio-visual speech separation (AVSS). First, the CTCNet learns hierarchical auditory and visual representations in a bottom-up manner in separate auditory and visual subnetworks, mimicking the functions of the auditory and visual cortical areas. Then, inspired by the large number of connections between cortical regions and the thalamus, the model fuses the auditory and visual information in a thalamic subnetwork through top-down connections. Finally, the model transmits this fused information back to the auditory and visual subnetworks, and the above process is repeated several times. The results of experiments on three speech separation benchmark datasets show that CTCNet remarkably outperforms existing AVSS methods with considerablely fewer parameters. These results suggest that mimicking the anatomical connectome of the mammalian brain has great potential for advancing the development of deep neural networks. Project repo is https://github.com/JusperLee/CTCNet.

This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image, we treat the prompt as an extra and independent learnable component. We show that the strategy of reconciling the prompt and the image matters, and find that warping the prompt around a properly shrinked image empirically works the best. Second, we re-introduce two "old tricks" commonly used in building transferable adversarial examples, i.e., input diversity and gradient normalization, into visual prompting. These techniques improve optimization and enable the prompt to generalize better. We provide extensive experimental results to demonstrate the effectiveness of our method. Using a CLIP model, our prompting method sets a new record of 82.8% average accuracy across 12 popular classification datasets, substantially surpassing the prior art by +5.6%. It is worth noting that this prompting performance already outperforms linear probing by +2.1% and can even match fully fine-tuning in certain datasets. In addition, our prompting method shows competitive performance across different data scales and against distribution shifts. The code is publicly available at https://github.com/UCSC-VLAA/EVP.

Multivariate time series forecasting constitutes important functionality in cyber-physical systems, whose prediction accuracy can be improved significantly by capturing temporal and multivariate correlations among multiple time series. State-of-the-art deep learning methods fail to construct models for full time series because model complexity grows exponentially with time series length. Rather, these methods construct local temporal and multivariate correlations within subsequences, but fail to capture correlations among subsequences, which significantly affect their forecasting accuracy. To capture the temporal and multivariate correlations among subsequences, we design a pattern discovery model, that constructs correlations via diverse pattern functions. While the traditional pattern discovery method uses shared and fixed pattern functions that ignore the diversity across time series. We propose a novel pattern discovery method that can automatically capture diverse and complex time series patterns. We also propose a learnable correlation matrix, that enables the model to capture distinct correlations among multiple time series. Extensive experiments show that our model achieves state-of-the-art prediction accuracy.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.