Neural image compression has surpassed state-of-the-art traditional codecs (H.266/VVC) for rate-distortion (RD) performance, but suffers from large complexity and separate models for different rate-distortion trade-offs. In this paper, we propose an Efficient single-model Variable-bit-rate Codec (EVC), which is able to run at 30 FPS with 768x512 input images and still outperforms VVC for the RD performance. By further reducing both encoder and decoder complexities, our small model even achieves 30 FPS with 1920x1080 input images. To bridge the performance gap between our different capacities models, we meticulously design the mask decay, which transforms the large model's parameters into the small model automatically. And a novel sparsity regularization loss is proposed to mitigate shortcomings of $L_p$ regularization. Our algorithm significantly narrows the performance gap by 50% and 30% for our medium and small models, respectively. At last, we advocate the scalable encoder for neural image compression. The encoding complexity is dynamic to meet different latency requirements. We propose decaying the large encoder multiple times to reduce the residual representation progressively. Both mask decay and residual representation learning greatly improve the RD performance of our scalable encoder. Our code is at https://github.com/microsoft/DCVC.
In this study, we investigate the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using one or a few reference images. Building upon previous research that has focused on Target-domain Consistency, Large Diversity, and Cross-domain Consistency, we conclude two additional desired properties for GDA: Memory and Domain Association. To meet these properties, we proposed a novel method Domain Re-Modulation (DoRM). Specifically, DoRM freezes the source generator and employs additional mapping and affine modules (M&A module) to capture the attributes of the target domain, resulting in a linearly combinable domain shift in style space. This allows for high-fidelity multi-domain and hybrid-domain generation by integrating multiple M&A modules in a single generator. DoRM is lightweight and easy to implement. Extensive experiments demonstrated the superior performance of DoRM on both one-shot and 10-shot GDA, both quantitatively and qualitatively. Additionally, for the first time, multi-domain and hybrid-domain generation can be achieved with a minimal storage cost by using a single model. The code will be available at https://github.com/wuyi2020/DoRM.
In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal. The annotating of suspicious regions is easily affected by factors such as workers' emotional fluctuations and judgment standard, resulting in noisy labels, which in turn leads to missing and false detections, and ultimately leads to inconsistent judgments of product quality. Unlike the usual noisy labels, the ones used for surface defect detection appear to be inconsistent rather than mislabeled. The noise occurs in almost every label and is difficult to correct or evaluate. In this paper, we proposed a framework that learns trustworthy models from noisy labels for surface defect defection. At first, to avoid the negative impact of noisy labels on the model, we represent the suspicious regions with consistent and precise elements at the pixel-level and redesign the loss function. Secondly, without changing network structure and adding any extra labels, pluggable spatially correlated Bayesian module is proposed. Finally, the defect discrimination confidence is proposed to measure the uncertainty, with which anomalies can be identified as defects. Our results indicate not only the effectiveness of the proposed method in learning from noisy labels, but also robustness and real-time performance.
When perceiving the world from multiple viewpoints, humans have the ability to reason about the complete objects in a compositional manner even when the object is completely occluded from partial viewpoints. Meanwhile, humans can imagine the novel views after observing multiple viewpoints. The remarkable recent advance in multi-view object-centric learning leaves some problems: 1) the partially or completely occluded shape of objects can not be well reconstructed. 2) the novel viewpoint prediction depends on expensive viewpoint annotations rather than implicit view rules. This makes the agent fail to perform like humans. In this paper, we introduce a time-conditioned generative model for videos. To reconstruct the complete shape of the object accurately, we enhance the disentanglement between different latent representations: view latent representations are jointly inferred based on the Transformer and then cooperate with the sequential extension of Slot Attention to learn object-centric representations. The model also achieves the new ability: Gaussian processes are employed as priors of view latent variables for generation and novel-view prediction without viewpoint annotations. Experiments on multiple specifically designed synthetic datasets have shown that the proposed model can 1) make the video decomposition, 2) reconstruct the complete shapes of objects, and 3) make the novel viewpoint prediction without viewpoint annotations.
Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.
As the deep learning rapidly promote, the artificial texts created by generative models are commonly used in news and social media. However, such models can be abused to generate product reviews, fake news, and even fake political content. The paper proposes a solution for the Russian Artificial Text Detection in the Dialogue shared task 2022 (RuATD 2022) to distinguish which model within the list is used to generate this text. We introduce the DeBERTa pre-trained language model with multiple training strategies for this shared task. Extensive experiments conducted on the RuATD dataset validate the effectiveness of our proposed method. Moreover, our submission ranked second place in the evaluation phase for RuATD 2022 (Multi-Class).
Estimating precise metric depth and scene reconstruction from monocular endoscopy is a fundamental task for surgical navigation in robotic surgery. However, traditional stereo matching adopts binocular images to perceive the depth information, which is difficult to transfer to the soft robotics-based surgical systems due to the use of monocular endoscopy. In this paper, we present a novel framework that combines robot kinematics and monocular endoscope images with deep unsupervised learning into a single network for metric depth estimation and then achieve 3D reconstruction of complex anatomy. Specifically, we first obtain the relative depth maps of surgical scenes by leveraging a brightness-aware monocular depth estimation method. Then, the corresponding endoscope poses are computed based on non-linear optimization of geometric and photometric reprojection residuals. Afterwards, we develop a Depth-driven Sliding Optimization (DDSO) algorithm to extract the scaling coefficient from kinematics and calculated poses offline. By coupling the metric scale and relative depth data, we form a robust ensemble that represents the metric and consistent depth. Next, we treat the ensemble as supervisory labels to train a metric depth estimation network for surgeries (i.e., MetricDepthS-Net) that distills the embeddings from the robot kinematics, endoscopic videos, and poses. With accurate metric depth estimation, we utilize a dense visual reconstruction method to recover the 3D structure of the whole surgical site. We have extensively evaluated the proposed framework on public SCARED and achieved comparable performance with stereo-based depth estimation methods. Our results demonstrate the feasibility of the proposed approach to recover the metric depth and 3D structure with monocular inputs.
The appearance of the same object may vary in different scene images due to perspectives and occlusions between objects. Humans can easily identify the same object, even if occlusions exist, by completing the occluded parts based on its canonical image in the memory. Achieving this ability is still a challenge for machine learning, especially under the unsupervised learning setting. Inspired by such an ability of humans, this paper proposes a compositional scene modeling method to infer global representations of canonical images of objects without any supervision. The representation of each object is divided into an intrinsic part, which characterizes globally invariant information (i.e. canonical representation of an object), and an extrinsic part, which characterizes scene-dependent information (e.g., position and size). To infer the intrinsic representation of each object, we employ a patch-matching strategy to align the representation of a potentially occluded object with the canonical representations of objects, and sample the most probable canonical representation based on the category of object determined by amortized variational inference. Extensive experiments are conducted on four object-centric learning benchmarks, and experimental results demonstrate that the proposed method not only outperforms state-of-the-arts in terms of segmentation and reconstruction, but also achieves good global object identification performance.
The flourishing blossom of deep learning has witnessed the rapid development of Chinese character recognition. However, it remains a great challenge that the characters for testing may have different distributions from those of the training dataset. Existing methods based on a single-level representation (character-level, radical-level, or stroke-level) may be either too sensitive to distribution changes (e.g., induced by blurring, occlusion, and zero-shot problems) or too tolerant to one-to-many ambiguities. In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of both radical and stroke levels in a decent way. We propose a two-stage decomposition framework, where a Feature-to-Radical Decoder perceives radical structures and radical regions, and a Radical-to-Stroke Decoder further predicts the stroke sequences according to the features of radical regions. The generated radical structures and stroke sequences are encoded as a Radical-Structured Stroke Tree (RSST), which is fed to a Tree-to-Character Translator based on the proposed Weighted Edit Distance to match the closest candidate character in the RSST lexicon. Our extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art single-level methods by increasing margins as the distribution difference becomes more severe in the blurring, occlusion, and zero-shot scenarios, which indeed validates the robustness of the proposed method.