Canada

We introduce a novel task of 3D visual grounding in monoc-
ular RGB images using language descriptions with both ap-
pearance and geometry information. Specifically, we build
a large-scale dataset, Mono3DRefer, which contains 3D ob-
ject targets with their corresponding geometric text descrip-
tions, generated by ChatGPT and refined manually. To fos-
ter this task, we propose Mono3DVG-TR, an end-to-end
transformer-based network, which takes advantage of both
the appearance and geometry information in text embeddings
for multi-modal learning and 3D object localization. Depth
predictor is designed to explicitly learn geometry features.
The dual text-guided adapter is proposed to refine multiscale
visual and geometry features of the referred object. Based on
depth-text-visual stacking, the decoder fuses object-level ge-
ometric cues and visual appearance into a learnable query.
Comprehensive benchmarks and some insightful analyses are
provided for developing Mono3DVG. Extensive comparisons
and ablation studies show that our method significantly out-
performs all baselines. The dataset and code will be released

AAAI 2024

Mono3DVG: 3D Visual Grounding in Monocular Images

cv: scene analysis & understanding

cv: 3d computer vision

cv: multi-modal vision

cv: language and vision

cv: object detection & categorization

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 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.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/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. 

Given a composite image with photographic object and painterly background, painterly image harmonization targets at stylizing the composite object to be compatible with the background. Despite the competitive performance of existing painterly harmonization works, they did not fully leverage the painterly objects in artistic paintings. In this work, we explore learning from painterly objects for painterly image harmonization. In particular, we learn a mapping from background style and object information to object style based on painterly objects in artistic paintings. With the learnt mapping, we can hallucinate the target style of composite object, which is used to harmonize encoder feature maps to produce the harmonized image. Extensive experiments on the benchmark dataset demonstrate the effectiveness of our proposed method.

Painterly Image Harmonization by Learning from Painterly Objects

Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that retain access to past samples. In this paper,  to solve the  exemplar-free CIL problem, we propose a Dual-Stream Analytic Learning (DS-AL) approach. The DS-AL contains a main stream offering an analytical (i.e., closed-form) linear solution, and a compensation stream improving the inherent under-fitting limitation due to adopting linear mapping. The main stream redefines the CIL problem into a Concatenated Recursive Least Squares (C-RLS) task, allowing an equivalence between the CIL and its joint-learning counterpart. The compensation stream is governed by a Dual-Activation Compensation (DAC) module. This module re-activates the embedding with a different activation function from the main stream one, and seeks fitting compensation by projecting the embedding to the null space of the main stream's linear mapping. Empirical results demonstrate that the DS-AL, despite being an exemplar-free technique, delivers performance comparable with or better than that of replay-based methods across various datasets, including CIFAR-100, ImageNet-100 and ImageNet-Full. Additionally, the C-RLS' equivalent property allows the DS-AL to execute CIL in a phase-invariant manner. This is evidenced by a never-before-seen 500-phase CIL ImageNet task, which performs on a level identical to a 5-phase one.

DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning | VIDEO

Collaborative Filtering (CF) recommender models highly depend on user-item interactions to learn CF representations, thus falling short of recommending cold-start items. To address this issue, prior studies mainly introduce item features (e.g., thumbnails) for cold-start item recommendation. They learn a feature extractor on warm-start items to align feature representations with interactions, and then leverage the feature extractor to extract the feature representations of cold-start items for interaction prediction. Unfortunately, the features of cold-start items, especially the popular ones, tend to diverge from those of warm-start ones due to temporal feature shifts, preventing the feature extractor from accurately learning feature representations of cold-start items. 
To alleviate the impact of temporal feature shifts, we consider using Distributionally Robust Optimization (DRO) to enhance the generation ability of the feature extractor. Nonetheless, existing DRO methods face an inconsistency issue: the worse-case warm-start items emphasized during DRO training might not align well with the cold-start item distribution. To capture the temporal feature shifts and combat this inconsistency issue, we propose a novel temporal DRO with new optimization objectives, namely, 1) to integrate a worst-case factor to improve the worst-case performance, and 2) to devise a shifting factor to capture the shifting trend of item features and enhance the optimization of the potentially popular groups in cold-start items. Substantial experiments on three real-world datasets validate the superiority of our temporal DRO in enhancing the generalization ability of cold-start recommender models.

Temporally and Distributionally Robust Optimization for Cold-Start Recommendation

The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background distinction, and plurality of instances. To tackle these issues, we first introduce a novel conceptual framework called Supervision Interpolation (SI), which offers a fresh perspective on interpolation-based augmentations by relaxing and generalizing Mixup. Based on SI, we propose LossMix, a simple yet versatile and effective regularization that enhances the performance and robustness of object detectors and more. Our key insight is that we can effectively regularize the training on mixed data by interpolating their loss errors instead of ground truth labels. Empirical results on the PASCAL VOC and MS COCO datasets demonstrate that LossMix can consistently outperform state-of-the-art methods widely adopted for detection. Furthermore, by jointly leveraging LossMix with unsupervised domain adaptation, we successfully improve existing approaches and set a new state of the art for cross-domain object detection.

Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond

With the rapid development of Internet and Web techniques, Cross-Domain Recommendation (CDR) models have been widely explored for resolving the data-sparsity
and cold-start problem. Meanwhile, most CDR models should utilize explicit domain-shareable information (e.g., overlapped users or items) for knowledge transfer across domains. However, this assumption may not be always satisfied since users and items are always non-overlapped in real practice. The performance of many previous works will be severely impaired when these domain-shareable information are not available. To address the aforementioned issues, we propose the Joint Preference Exploration and Dynamic Embedding Transportation model (JPEDET) in this paper which is a novel framework for solving the CDR problem when users and items are non-overlapped. JPEDET includes two main modules, i.e., joint preference exploration module and dynamic embedding transportation module. The joint preference exploration module aims to fuse rating and review information for modelling user preferences. The dynamic embedding transportation module is set to share knowledge via neural ordinary equations for dual transformation across domains. Moreover, we innovatively propose the dynamic transport flow equipped with linear interpolation guidance on barycentric Wasserstein path for achieving accurate and bidirectional transformation. Our empirical study on Amazon datasets demonstrates that JPEDET significantly outperforms the state-of-the-art models under the CDR setting.

Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation | VIDEO

Program synthesis is the task of automatically generating code based on a specification. In Syntax-Guided Synthesis (SyGuS) this specification is a combination of a syntactic template and a logical formula, and the result 
is guaranteed to satisfy both. We present a reinforcement-learning guided algorithm for SyGuS which uses Monte-Carlo Tree Search (MCTS) to search the space of candidate solutions. Our algorithm learns policy and value functions which, combined with the upper confidence bound for trees, allow it to balance exploration and exploitation. 
A common challenge in applying machine learning approaches to syntax-guided synthesis is the scarcity of training data. To address this, we present a method for automatically generating training data for SyGuS based on \emph{anti-unification} of existing first-order satisfiability problems, which we use to train our MCTS policy. We implement and evaluate this setup and demonstrate that learned policy and value improve the synthesis performance over a baseline by over 26 percentage points in the training and testing sets. Our tool outperforms state-of-the-art tool cvc5 on the training set and performs comparably in terms of the total number of problems solved on the testing set (solving 23\% of the benchmarks on which cvc5 fails). We make our data set publicly available, to enable further application of machine learning methods to the SyGuS problem.

Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis

Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient modules, such as popular inverted residual blocks. Prior depth pruning methods by reducing network depths are not suitable for pruning some efficient models due to the existence of some normalization layers. Moreover, finetuning subnet with directly removing activation layers would corrupt the original model weights, hindering the pruned model from achieving high performance. To address these issues, we propose a novel depth pruning method for efficient models. Our approach proposes a novel block pruning strategy and progressive training method for the subnet. Additionally, we extend our pruning method to vision transformer models. Experimental results demonstrate that our method consistently outperforms existing depth pruning methods across various pruning configurations. We obtained three pruned ConvNeXtV1 models with our method applying on ConvNeXtV1, which surpass most SOTA efficient models with comparable inference performance. Our method also achieves state-of-the-art pruning performance on the vision transformer model.

UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer

Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to study label-efficient object detection methods on aerial images. In this work, we propose a zero-shot method for aerial object detection named visual Description Regularization, or DescReg. 
Concretely, we identify the weak semantic-visual correlation of the aerial objects and aim to address the challenge with prior descriptions of their visual appearance. Instead of directly encoding the descriptions into class embedding space which suffers from the representation gap problem, we propose to infuse the prior inter-class visual similarity conveyed in the descriptions into the embedding learning. The infusion process is accomplished with a newly designed similarity-aware triplet loss which incorporates structured regularization on the representation space. We conduct extensive experiments with three challenging aerial object detection datasets, including DIOR, xView, and DOTA. The results demonstrate that DescReg significantly outperforms the state-of-the-art ZSD methods with complex projection designs and generative frameworks, e.g., DescReg outperforms 
best reported ZSD method on DIOR by 4.5 mAP on unseen classes and 8.1 in HM. We further show the generalizability of DescReg by integrating it into generative ZSD methods as well as varying the detection architecture.
Codes will be released at https://github.com/zq-zang/DescReg.

Zero-Shot Aerial Object Detection with Visual Description Regularization

The Transformer architecture has been popular in recent crowd counting work since it breaks the limited receptive field of traditional CNNs. However, since crowd images always contain a large number of similar patches, the self-attention mechanism in Transformer tends to find an over-simplified solution where the attention maps of almost all patches are identical. In this paper, we address this problem by proposing Gramformer: a graph-modulated transformer to enhance the network by adjusting the attention and input node features respectively on the basis of two different types of graphs. Firstly, an attention graph is proposed to diverse attention maps to attend to complementary information. The graph is building upon the dissimilarities between patches, modulating the attention in an anti-similarity fashion. Secondly, a feature-based centrality encoding is proposed to discover the centrality positions or importance of nodes. We encode them with a proposed centrality indices scheme to modulate the node features and similarity relationships. Extensive experiments on four challenging crowd counting datasets have validated the competitiveness of the proposed method. Codes will be available.

Gramformer: Learning Crowd Counting via Graph-Modulated Transformer

Recent advances in zero-shot text-to-3D human generation, which employ the human model prior (e.g., SMPL) or Score Distillation Sampling (SDS) with pre-trained text-to-image diffusion models, have been groundbreaking. However, SDS may provide inaccurate gradient directions under the weak diffusion guidance, as it tends to produce over-smoothed results and generate body textures that are inconsistent with the detailed mesh geometry. Therefore, directly leverage existing strategies for high-fidelity text-to-3D human texturing is challenging. In this work, we propose a model called PaintHuman to addresses the challenges from two aspects. We first propose a novel score function, Denoised Score Distillation (DSD), which directly modifies the SDS by introducing negative gradient components to iteratively correct the gradient direction and generate high-quality textures. In addition, we use the depth map as a geometric guidance to ensure the texture is semantically aligned to human mesh surfaces. To guarantee the quality of rendered results, we employ geometry-aware networks to predict surface materials and render realistic human textures. Extensive experiments, benchmarked against state-of-the-art methods, validate the efficacy of our approach.

Downloads

Next from AAAI 2024

Painterly Image Harmonization by Learning from Painterly Objects

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES