United States

The generation of a virtual digital avatar is a crucial research topic in the field of computer vision. Many existing works utilize Neural Radiance Fields (NeRF) to address this issue and have achieved impressive results. However, previous works assume the images of the training person are available and fixed while the appearances and poses of a subject could constantly change and increase in real-world scenarios. How to update the human avatar but also maintain the ability to render the old appearance of the person is a practical challenge. One trivial solution is to combine the existing virtual avatar models based on NeRF with continual learning methods. However, there are some critical issues in this approach: learning new appearances and poses can cause the model to forget past information, which in turn leads to a degradation in the rendering quality of past appearances, especially color bleeding issues, and incorrect human body poses. In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module. Overall, our model requires only limited data collection to quickly fine-tune the model while avoiding catastrophic forgetting, thus achieving a maintainable virtual avatar. The experimental results validate the effectiveness of our MaintaAvatar model.

AAAI 2025

MaintaAvatar: A Maintainable Avatar based on Neural Radiance Fields by Continual Learning

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Open-vocabulary panoptic segmentation aims to segment and classify everything in diverse scenes across an unbounded vocabulary. Existing methods typically employ two-stage or single-stage framework. The two-stage framework involves cropping the image multiple times using masks generated by a mask generator, followed by feature extraction, while the single-stage framework relies on a heavyweight mask decoder to make up for the lack of spatial position information through self-attention and cross-attention in multiple stacked Transformer blocks. Both methods incur substantial computational overhead, thereby hindering the efficiency of model inference. To fill the gap in efficiency, we propose EOV-Seg, a novel single-stage, shared, efficient, and spatial-aware framework designed for open-vocabulary panoptic segmentation. Specifically, EOV-Seg innovates in two aspects. First, a Vocabulary-Aware Selection (VAS) module is proposed to improve the semantic comprehension of visual aggregated features and alleviate the feature interaction burden on the mask decoder. Second, we introduce a Two-way Dynamic Embedding Experts (TDEE), which efficiently utilizes the spatial awareness capabilities of ViT-based CLIP backbone. To the best of our knowledge, EOV-Seg is the first open-vocabulary panoptic segmentation framework towards efficiency, which runs faster and achieves competitive performance compared with state-of-the-art methods. Specifically, with COCO training only, EOV-Seg achieves 24.2 PQ, 31.6 mIoU, and 12.7 FPS on the ADE20K dataset for panoptic and semantic segmentation tasks and the inference time of EOV-Seg is 4~21 times faster than state-of-the-art methods. Especially, equipped with ResNet-50 backbone, EOV-Seg runs 25 FPS with only 71M parameters on a single RTX 3090 GPU. The code will be public.

EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation

Few-shot-learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labeled samples of the new classes (support set) as reference. So far, plenty of algorithms involve training data augmentation to improve the generalization capability of FSL models, but outlier queries or support images during inference can still pose great generalization challenges.
In this work, to reduce the bias caused by the outlier samples, we generate additional test-class samples by combining original samples with suitable train-class samples via a generative image combiner. Then, we obtain averaged features via an augmentor, which leads to more typical representations through the averaging. We experimentally and theoretically demonstrate the effectiveness of our method, e.g., obtaining a test accuracy improvement proportion of around 10\% (e.g., from 46.86\% to 53.28\%) for trained FSL models. Importantly, given pretrained image combiner, our method is training-free for off-the-shelf FSL models, whose performance can be improved without extra datasets nor further training of the models themselves. Codes are publicly available at \url{https://anonymous.4open.science/r/FSL-Rectifier-4DC4}.

FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation

Deep neural networks (DNNs) have achieved significant success across various tasks, but ensuring reliable uncertainty estimates, known as model calibration, is crucial for their safe and effective deployment. Modern DNNs often suffer from overconfidence, leading to miscalibration. We propose a novel post-hoc calibration method called feature clipping (FC) to address this issue. FC involves clipping feature values to a specified threshold, effectively increasing entropy in high calibration error samples while maintaining the information in low calibration error samples. This process reduces the overconfidence in predictions, improving the overall calibration of the model. Our extensive experiments on datasets such as CIFAR-10, CIFAR-100, and ImageNet, and models including CNNs and transformers, demonstrate that FC consistently enhances calibration performance. Additionally, we provide a theoretical analysis that validates the effectiveness of our method. As the first calibration technique based on feature modification, feature clipping offers a novel approach to improving model calibration, showing significant improvements over both post-hoc and train-time calibration methods and pioneering a new avenue for feature-based model calibration.

Feature Clipping for Uncertainty Calibration

Generating high-quality whole-body human object interaction motion sequences is becoming increasingly important in various fields such as animation, VR/AR, and robotics. The main challenge of this task lies in determining the level of involvement of each hand given the complex shapes of objects in different sizes and their different motion trajectories, while ensuring strong grasping realism and guaranteeing the coordination of movement in all body parts. Contrasting with existing work, which either generates human interaction motion sequences without detailed hand grasping poses or only models a static grasping pose, we propose a simple yet effective framework that jointly models the relationship between the body, hands, and the given object motion sequences within a single diffusion model. To guide our network in perceiving the object's spatial position and learning more natural grasping poses, we introduce novel contact-aware losses and incorporate a data-driven, carefully designed guidance. Experimental results demonstrate that our approach outperforms the state-of-the-art method and generates plausible whole-body motion sequences. We will release our code upon acceptance.

DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model

Diffusion models have demonstrated remarkable synthesis quality and  diversity in generating co-speech gestures. However, the computationally intensive sampling steps associated with diffusion models hinder their practicality in real-world applications. Hence,  we present DIDiffGes, for a Decoupled Semi-Implicit Diffusion model-based framework, that can synthesize high-quality, expressive gestures from speech using only a few sampling steps. Our approach leverages Generative Adversarial Networks (GANs) to enable large-step sampling for diffusion model. We decouple gesture data into body and hands distributions and further decompose them into marginal and conditional distributions. GANs model the marginal distribution implicitly, while L2 reconstruction loss learns the conditional distributions exciplictly. This strategy enhances GAN training stability and ensures expressiveness of generated full-body gestures. Our framework also learns to denoise root noise conditioned on local body representation, guaranteeing stability and realism. DIDiffGes can generate gestures from speech with just 10 sampling steps, without compromising quality and expressiveness, reducing the number of sampling steps by a factor of 100 compared to existing methods. Our user study reveals that our method outperforms state-of-the-art approaches in human likeness, appropriateness, and style correctness.

DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech

Nighttime Semantic Segmentation (NSS) is essential to many cutting-edge vision applications. However, existing technologies overly rely on massive labeled data, whose annotation is time-consuming and laborious. In this paper, we pioneer a new task focusing on exploring the potential of training strategy and framework design with limited annotation to achieve a high-performance Nighttime Semantic Segmentation. Insufficient information at very low labeling budgets can easily lead to under-optimization or overfitting of the model. Our solution comprises two main components: i) a novel region-based active sampling strategy called Contextual-Aware Region Query (CARQ), which identifies highly informative target nighttime regions for labeling; and ii) an innovative Fragmentation Synergy Active Domain Adaptation framework (FS-ADA), which progressively broadcasts the limited annotation to the unlabeled regions, achieving high performance with a minimal annotation budget. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art UDA-NSS and ADA-SS methods across four day-to-nighttime benchmarks, while with strong generalization to foggy, rainy, and snowy scenes. In particular only with 1% target nighttime data annotation, our method is on par with the mainstream fully-supervised methods.

The Parables of the Mustard Seed and the Yeast: Extremely Low-Budget, High-Performance Nighttime Semantic Segmentation

Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive perspective, focusing on capturing all details of a single image, which will misconstrue the specific image's irrelevant attributes (e.g., view, pose, and background) as the subject intrinsic attributes. This misconstruction leads to both overfitting or underfitting of irrelevant and intrinsic attributes of the subject, i.e., these attributes are over-represented or under-represented simultaneously, causing a trade-off between similarity and controllability. In this study, we argue an ideal subject representation can be achieved by a cross-differential perspective, i.e., decoupling subject intrinsic attributes from irrelevant attributes via contrastive learning,  which allows the model to focus more on intrinsic attributes through intra-consistency  (features of the same subject are spatially closer) and inter-distinctiveness (features of different subjects have distinguished differences). Specifically, we propose CustomContrast, a novel framework, which includes a Multilevel Contrastive Learning (MCL) paradigm and a Multimodal Feature Injection (MFI) Encoder. The MCL paradigm is used to extract intrinsic features of subjects from high-level semantics to low-level appearance through crossmodal semantic contrastive learning and multiscale appearance contrastive learning.  To facilitate contrastive learning, we introduce the MFI encoder to capture cross-modal representations. Extensive experiments show the effectiveness of CustomContrast in subject similarity and text controllability.

CustomContrast: A Multilevel Contrastive Perspective for Subject-Driven Text-to-Image Customization

Geo-entity resolution involves linking records that refer to the same entities across different spatial datasets, which underpins location-based services. Given the varying quality and reliability of geospatial data, this task is known to be challenging, as directly comparing the semantic-centric representations of two entities is no longer reliable. To robustify geo-entity resolution in this context, the main research question is how to effectively extend the current semantics-centric representations of geo-entity with geographical context from its spatial neighbors. Existing methods consider names from neighbor entities, but they struggle to fully utilize the unaligned neighbor attributes. In this paper, we investigate the representation of geographical context for robust geo-entity resolution and propose two adaptations that efficiently leverage unaligned geo-entity attributes across spatial neighbors: (1) A plugin module, namely Unaligned Message-Passing layer (UMP), that propagates unaligned neighbor features to integrate geo-context into the token embeddings output by language model; (2) a contextualized pretraining framework (CP) that allows the former to leverage unlabelled geo-entity data. Experiments show that our method surpasses the baseline methods, achieving higher F1 scores on 8 real-world geo-datasets in terms of robustness, with an improvement of up to 7.9%. The ablation study further justifies our proposal.

Unaligned Message-Passing and Contextualized-Pretraining for Robust Geo-Entity Resolution

Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, which leads to suboptimal rate-distortion results. In this paper, we propose a stereo image compression framework, named CAMSIC. CAMSIC independently transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model to capture both spatial and disparity dependencies, by introducing a novel content-aware masked image modeling (MIM) technique. Our content-aware MIM facilitates efficient bidirectional interaction between prior information and estimated tokens, which naturally obviates the need for an extra Transformer decoder. Experiments show that our stereo image codec achieves state-of-the-art rate-distortion performance on two stereo image datasets Cityscapes and InStereo2K with fast encoding and decoding speed.

CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression

While existing semi-supervised object detection (SSOD) methods perform well in general scenes, they encounter challenges in handling oriented objects in aerial images. 
We experimentally find three gaps between general and oriented object detection in semi-supervised learning: 
1) Sampling inconsistency: the common center sampling is not suitable for oriented objects with larger aspect ratios when selecting positive labels from labeled data. 
2) Assignment inconsistency: balancing the precision and localization quality of oriented pseudo-boxes poses greater challenges which introduces more noise when selecting positive labels from unlabeled data. 
3) Confidence inconsistency: there exists more mismatch between the predicted classification and localization qualities when considering oriented objects, affecting the selection of pseudo-labels. 
Therefore, we propose a Multi-clue Consistency Learning (MCL) framework to bridge gaps between general and oriented objects in semi-supervised detection. 
Specifically, considering various shapes of rotated objects, the Gaussian Center Assignment is specially designed to select the pixel-level positive labels from labeled data. 
We then introduce the Scale-aware Label Assignment to select pixel-level pseudo-labels instead of unreliable pseudo-boxes, which is a divide-and-rule strategy suited for objects with various scales. 
The Consistent Confidence Soft Label is adopted to further boost the detector by maintaining the alignment of the predicted results. 
Comprehensive experiments on DOTA-v1.5 and DOTA-v1.0 benchmarks demonstrate that our proposed MCL can achieve state-of-the-art performance in the semi-supervised oriented object detection task.

Premium content

Next from AAAI 2025

EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES