Canada

Language conditioned 3D object grounding aims to find the object within the 3D scene mentioned by natural language descriptions, which mainly depends on the matching between visual and natural language. Considerable improvement in grounding performance by improving the multi-modal fusion mechanism or bridging the gap between detection and matching, to improve grounding performance. However, several mismatches are ignored, i.e., mismatch in local visual representation and global sentence representation, and mismatch in visual space and corresponding label word space. In this paper, we propose cross-modal match for 3D grounding from mitigating these mismatches perspective. Specifically, to match local visual features with the global description sentence, we propose BEV (Bird&#39;s-eye-view) based global information embedding module. It projects multiple object proposal features into the BEV and the relations of different objects are accessed by the visual transformer which can model both positions and features with long-range dependencies. To circumvent the mismatch in feature spaces of different modalities, we propose cross-modal consistency learning. It performs cross-modal consistency constraints to convert the visual feature space into the label word feature space resulting in easier matching. Besides, we introduce label distillation loss and global distillation loss to drive these matches learning in a distillation way. We evaluate our method in mainstream evaluation settings on three datasets, and the results demonstrate the effectiveness of the proposed method.

AAAI 2024

Cross-Modal Match for Language Conditioned 3D Object Grounding

cross-modal match

language conditioned 3d object grounding

point cloud

Language conditioned 3D object grounding aims to find the object within the 3D scene mentioned by natural language descriptions, which mainly depends on the matching between visual and natural language. Considerable improvement in grounding performance by improving the multi-modal fusion mechanism or bridging the gap between detection and matching, to improve grounding performance. However, several mismatches are ignored, i.e., mismatch in local visual representation and global sentence representation, and mismatch in visual space and corresponding label word space. In this paper, we propose cross-modal match for 3D grounding from mitigating these mismatches perspective. Specifically, to match local visual features with the global description sentence, we propose BEV (Bird's-eye-view) based global information embedding module. It projects multiple object proposal features into the BEV and the relations of different objects are accessed by the visual transformer which can model both positions and features with long-range dependencies. To circumvent the mismatch in feature spaces of different modalities, we propose cross-modal consistency learning. It performs cross-modal consistency constraints to convert the visual feature space into the label word feature space resulting in easier matching. Besides, we introduce label distillation loss and global distillation loss to drive these matches learning in a distillation way. We evaluate our method in mainstream evaluation settings on three datasets, and the results demonstrate the effectiveness of the proposed method.

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. 

Information diffusion prediction plays a crucial role in understanding the propagation of information in social networks, encompassing both macroscopic and microscopic prediction tasks. Macroscopic prediction estimates the overall impact of information diffusion, while microscopic prediction focuses on identifying the next user to be influenced. While prior research often concentrates on one of these aspects, a few tackle both concurrently. These two tasks provide complementary insights into the diffusion process at different levels, revealing common traits and unique attributes. The exploration of leveraging common features across these tasks to enhance information prediction remains an underexplored avenue. In this paper, we propose an intuitive and effective model that addresses both macroscopic and microscopic prediction tasks. Our approach considers the interactions and dynamics among cascades at the macro level and incorporates the social homophily of users in social networks at the micro level. Additionally, we introduce adversarial training and orthogonality constraints to ensure the integrity of shared features. Experimental results on four datasets demonstrate that our model significantly outperforms state-of-the-art methods.

Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning

In this paper, we study the mistake bound of online kernel learning on a budget. We propose a new budgeted online kernel learning model, called Ahpatron, which significantly improves the mistake bound of previous work and resolves an open problem related to upper bounds of hypothesis space constraints. We first present an aggressive variant of Perceptron, named AVP, a model without budget, which uses an active updating rule. Then we design a new budget maintenance mechanism, which removes a half of examples, and projects the removed examples onto a hypothesis space spanned by the remaining examples. Ahpatron adopts the above mechanism to approximate AVP. Theoretical analyses prove that Ahpatron has tighter mistake bounds, and experimental results show that Ahpatron outperforms the state-of-the-art algorithms on the same or a smaller budget.

Ahpatron: A New Budgeted Online Kernel Learning Machine with Tighter Mistake Bound

How to frame (or crop) a photo often depends on the image subject and its context; e.g., a human portrait. Recent works have defined the subject-aware image cropping task as a nuanced and practical version of image cropping. We propose a weakly-supervised approach (GenCrop) to learn what makes a high-quality, subject-aware crop from professional stock images. Unlike supervised prior work, GenCrop requires no new manual annotations beyond the existing stock image collection. The key challenge in learning from this data, however, is that the images are already cropped and we do not know what regions were removed. Our insight is combine a library of stock images with a modern, pre-trained text-to-image diffusion model. The stock image collection provides diversity and its images serve as pseudo-labels for a good crop, while the text-image diffusion model is used to out-paint (i.e., outward inpainting) realistic uncropped images. Using this procedure, we are able to automatically generate a large dataset of cropped-uncropped training pairs to train a cropping model. Despite being weakly-supervised, GenCrop is competitive with state-of-the-art supervised methods and significantly better than comparable weakly-supervised baselines on quantitative and qualitative evaluation metrics.

Learning Subject-Aware Cropping by Outpainting Professional Photos | VIDEO

Equitability (EQ) in fair division requires that items be allocated such that all agents value the bundle they receive equally. With indivisible items, an equitable allocation may not exist, and hence we instead consider a meaningful analog, EQx, that requires equitability up to any item. EQx allocations exist for monotone, additive valuations. However, if (1) the agents' valuations are not additive or (2) the set of indivisible items includes both goods and chores (positively and negatively valued items), then prior to the current work it was not known whether EQx allocations exist or not. 

We study both the existence and efficient computation of EQx allocations. (1) For monotone valuations (not necessarily additive), we show that EQx allocations always exist. Also, for the large class of weakly well-layered valuations, EQx allocations can be found in polynomial time. Further, we prove that approximately EQx allocations can be computed efficiently under general monotone valuations.  (2) For non-monotone valuations, we show that an EQx allocation may not exist, even for two agents with additive valuations. Under some special cases, however, we show existence and efficient computability of EQx allocations. This includes the case of two agents with additive valuations where each item is either a good for every agent, or a chore for every agent.

Nearly Equitable Allocations beyond Additivity and Monotonicity

Textual style transfer is the task of transforming stylistic properties of text while preserving meaning. Target "styles" can be defined in numerous ways, ranging from single attributes (e.g. formality) to authorship (e.g. Shakespeare). Previous unsupervised style-transfer approaches generally rely on significant amounts of labeled data for only a fixed set of styles or require large language models. In contrast, we introduce a novel diffusion-based framework for general-purpose style transfer that can be flexibly adapted to arbitrary target styles at inference time. Our parameter-efficient approach, ParaGuide, leverages paraphrase-conditioned diffusion models alongside gradient-based guidance from both off-the-shelf classifiers and strong existing style embedders to transform the style of text while preserving semantic information. We validate the method on the Enron Email Corpus, with both human and automatic evaluations, and find that it outperforms strong baselines on formality, sentiment, and even authorship style transfer.

ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer

3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation process by leveraging scene-level labels. However, these methods have not effectively exploited the rich geometric information (such as shape and scale) and appearance information (such as color and texture) present in RGB-D scans. Furthermore, current approaches fail to fully leverage the point affinity that can be inferred from the feature extraction network, which is crucial for learning from weak scene-level labels. Additionally, previous work overlooks the detrimental effects of the long-tailed distribution of point cloud data in weakly supervised 3D semantic segmentation. To this end, this paper proposes a simple yet effective scene-level weakly supervised point cloud segmentation method with a newly introduced multi-modality point affinity inference module. The point affinity proposed in this paper is characterized by features from multiple modalities (e.g., point cloud and RGB), and is further refined by normalizing the classifier weights to alleviate the detrimental effects of long-tailed distribution without the need of the prior of category distribution. Extensive experiments on the ScanNet and S3DIS benchmarks verify the effectiveness of our proposed method, which outperforms the state-of-the-art by ~4% to ~ 6% mIoU.

Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a challenging task, and noise exists in the commonly used datasets. To address this issue, we propose SoftCLIP, a novel approach that relaxes the strict one-to-one constraint and achieves a soft cross-modal alignment by introducing a softened target, which is generated from the fine-grained intra-modal self-similarity. The intra-modal guidance is indicative to enable two pairs have some local similarities and model many-to-many relationships between the two modalities. Besides, since the positive still dominates in the softened target distribution, we disentangle the negatives in the distribution to further boost the relation alignment with the negatives in the cross-modal learning. Extensive experiments demonstrate the effectiveness of SoftCLIP. In particular, on ImageNet zero-shot classification task, using CC3M/CC12M as pre-training dataset, SoftCLIP brings a top-1 accuracy improvement of 6.8\%/7.2\% over the CLIP baseline.

SoftCLIP: Softer Cross-Modal Alignment Makes CLIP Stronger

Differing from traditional semi-supervised learning, class-imbalanced semi-supervised learning presents two distinct challenges: (1) The imbalanced distribution of training samples leads to model bias towards certain classes, and (2) the distribution of unlabeled samples is unknown and potentially distinct from that of labeled samples, which further contributes to class bias in the pseudo-labels during the training. To address these dual challenges, we introduce a novel approach called Twice Class Bias Correction (TCBC). We begin by utilizing an estimate of the class distribution from the participating training samples to correct the model, enabling it to learn the posterior probabilities of samples under a class-balanced prior. This correction serves to alleviate the inherent class bias of the model. Building upon this foundation, we further estimate the class bias of the current model parameters during the training process. We apply a secondary correction to the model's pseudo-labels for unlabeled samples, aiming to make the assignment of pseudo-labels across different classes of unlabeled samples as equitable as possible. Through extensive experimentation on CIFAR10/100-LT, STL10-LT, and the sizable long-tailed dataset SUN397, we provide conclusive evidence that our proposed TCBC method reliably enhances the performance of class-imbalanced semi-supervised learning.

Twice Class Bias Correction for Imbalanced Semi-supervised Learning

Neural style transfer (NST) has evolved significantly in recent years. Yet, despite its rapid progress and advancement, existing NST methods either struggle to transfer aesthetic information from a style effectively or suffer from high computational costs and inefficiencies in feature disentanglement due to using pre-trained models. This work proposes a lightweight but effective model, AesFA---Aesthetic Feature-Aware NST. The primary idea is to decompose the image via its frequencies to better disentangle aesthetic styles from the reference image while training the entire model in an end-to-end manner to exclude pre-trained models at inference completely. To improve the network's ability to extract more distinct representations and further enhance the stylization quality, this work introduces a new aesthetic feature: contrastive loss. Extensive experiments and ablations show the approach not only outperforms recent NST methods in terms of stylization quality, but it also achieves faster inference. Codes are available at https://github.com/Sooyyoungg/AesFA.

AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer

Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown objects while integrating learned knowledge for future tasks. However, the level of "unknownness" varies significantly depending on the context. For example, a tree is typically considered part of the background in a self-driving scene, but it may be significant in a household context. We argue that this contextual information should already be embedded within the known classes. In other words, there should be a semantic or latent structure relationship between the known and unknown items to be discovered. Motivated by this observation, we propose Hyp-OW, a method that learns and models hierarchical representation of known items through a SuperClass Regularizer. Leveraging this representation allows us to effectively detect unknown objects using a similarity distance-based relabeling module. Extensive experiments on benchmark datasets demonstrate the effectiveness of Hyp-OW, achieving improvement in both known and unknown detection (up to 6 percent). These findings are particularly pronounced in our newly designed benchmark, where a strong hierarchical structure exists between known and unknown objects.

Content not yet available

Cross-Modal Match for Language Conditioned 3D Object Grounding

Downloads

Next from AAAI 2024

Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

Cross-Modal Match for Language Conditioned 3D Object Grounding

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads