Canada

Neural networks with self-attention (a.k.a. Transformers) like ViT and Swin have emerged as a better alternative to traditional convolutional neural networks (CNNs). However, our understanding of how the new architecture works is still limited. In this paper, we focus on the phenomenon that Transformers show higher robustness against corruptions than CNNs, while not being overconfident. This is contrary to the intuition that robustness increases with confidence. We resolve this contradiction by empirically investigating how the output of the penultimate layer moves in the representation space as the input data moves linearly within a small area. In particular, we show the following. (1) While CNNs exhibit fairly linear relationship between the input and output movements, Transformers show nonlinear relationship for some data. For those data, the output of Transformers moves in a curved trajectory as the input moves linearly. (2) When a data is located in a curved region, it is hard to move it out of the decision region since the output moves along a curved trajectory instead of a straight line to the decision boundary, resulting in high robustness of Transformers. (3) If a data is slightly modified to jump out of the curved region, the movements afterwards become linear and the output goes to the decision boundary directly. In other words, there does exist a decision boundary near the data, which is hard to find only because of the curved representation space. This explains the underconfident prediction of Transformers. Finally, we also share our additional findings, regarding what contributes to the curved representation space of Transformers and how the curvedness evolves during training.

AAAI 2024

Curved Representation Space of Vision Transformers

ml: evaluation and analysis (machine learning)

ml: classification and regression

ml: deep neural architectures

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. 

Image inpainting is in full bloom accompanied by the progress of convolutional neural networks (CNNs) and transformers, revolutionizing the practical management of abnormity disposal, image editing, etc. However, due to the ever-mounting image resolutions and missing areas, the challenges of distorted long-range dependencies from cluttered background distributions and reduced reference information in image domain inevitably rise, which further cause severe performance degradation. To address the challenges, we propose a novel large-portion image inpainting approach, namely the Structure-Guided Synergism Transformer (SyFormer), to rectify the discrepancies in feature representation and enrich the structural cues from limited reference. Specifically, we devise a dual-routing filtering module that employs a progressive filtering strategy to eliminate invalid noise interference and establish global-level texture correlations. Simultaneously, the structurally compact perception module maps an affinity matrix within the introduced structural priors from a structure-aware generator, assisting in matching and filling the corresponding patches of large-proportionally damaged images. Moreover, we carefully assemble the aforementioned modules to achieve feature complementarity. Finally, a feature decoding alignment scheme is introduced in the decoding process, which meticulously achieves texture amalgamation across hierarchical features. Extensive experiments are conducted on two publicly available datasets, i.e., CelebA-HQ and Places2, to qualitatively and quantitatively demonstrate the superiority of our model over state-of-the-arts.

SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting | VIDEO

Reconstructing a dynamic human with loose clothing is an important but difficult task. To address this challenge, we propose a method named DLCA-Recon to create human avatars from monocular videos. The distance from loose clothing to the underlying body rapidly changes in every frame when the human freely moves and acts. Previous methods lack effective geometric initialization and constraints for guiding the optimization of deformation to explain this dramatic change, resulting in the discontinuous and incomplete reconstruction surface.To model the deformation more accurately, we propose to initialize an estimated 3D clothed human in the canonical space, as it is easier for deformation fields to learn from the clothed human than from SMPL.With both representations of explicit mesh and implicit SDF, we utilize the physical connection information between consecutive frames and propose a dynamic deformation field (DDF) to optimize deformation fields. DDF accounts for contributive forces on loose clothing to enhance the interpretability of deformations and effectively capture the free movement of loose clothing. Moreover, we propagate SMPL skinning weights to each individual and refine pose and skinning weights during the optimization to improve skinning transformation. Based on more reasonable initialization and DDF, we can simulate real-world physics more accurately. Extensive experiments on public and our own datasets validate that our method can produce superior results for humans with loose clothing compared to the SOTA methods.

DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos

The theory of Bayesian learning incorporates the use of Student-t Processes to model heavy-tailed distributions and datasets with outliers. However, despite Student-t Processes having a similar computational complexity as Gaussian Processes, there has been limited emphasis on the sparse representation of this model. This is mainly due to the increased difficulty in modeling and computation compared to previous sparse Gaussian Processes. Our motivation is to address the need for a sparse representation framework that reduces computational complexity, allowing Student-t Processes to be more flexible for real-world datasets. To achieve this, we leverage the conditional distribution of Student-t Processes to introduce sparse inducing points. Bayesian methods and variational inference are then utilized to derive a well-defined lower bound, facilitating more efficient optimization of our model through stochastic gradient descent. We propose two methods for computing the variational lower bound, one utilizing Monte Carlo sampling and the other employing Jensen's inequality to compute the KL regularization term in the loss function. We propose adopting these approaches as viable alternatives to Gaussian processes when the data might contain outliers or exhibit heavy-tailed behavior, and we provide specific recommendations for their applicability. We evaluate the two proposed approaches on various synthetic and real-world datasets from UCI and Kaggle, demonstrating their effectiveness compared to baseline methods in terms of computational complexity and accuracy, as well as their robustness to outliers.

Sparse Variational Student-t Processes | VIDEO

We study the budget aggregation problem in which a set of strategic voters must split a finite divisible resource (such as money or time) among a set of competing projects. Our goal is twofold: We seek truthful mechanisms that provide fairness guarantees to the projects. For the first objective, we focus on the class of moving phantom mechanisms (Freeman et al. 2021), which are -- to this day -- essentially the only known truthful mechanisms in this setting. For project fairness, we consider the mean division as a fair baseline, and bound the maximum difference between the funding received by any project and this baseline. We propose a novel and simple moving phantom mechanism that provides optimal project fairness guarantees. As a corollary of our results, we show that our new mechanism minimizes the L1 distance to the mean (a measure suggested by Caragiannis, Christodoulou, and Protopapas (2022)) for three projects and gives the first non-trivial bounds on this quantity for more than three projects.

Project-Fair and Truthful Mechanisms for Budget Aggregation

Image-text matching bridges vision and language, which is a fundamental task in multimodal intelligence. Its key challenge lies in how to capture visual-semantic relevance. Fine-grained semantic interactions come from fragment alignments between image regions and text words. However, not all fragments contribute to image-text relevance, and many existing methods are devoted to mining the vital ones to measure the relevance accurately. How well image and text relate depends on the degree of semantic sharing between them. Treating the degree as an effect and fragments as its possible causes, we define those indispensable causes for the generation of the degree as necessary undertakers, i.e., if any of them did not occur, the relevance would be no longer valid. In this paper, we revisit image-text matching in the causal view and uncover inherent causal properties of relevance generation. Then we propose a novel theoretical prototype for estimating the probability-of-necessity of fragments, PN_f, for the degree of semantic sharing by means of causal inference, and further design a Necessary Undertaker Identification Framework (NUIF) for image-text matching, which explicitly formalizes the fragment's contribution to image-text relevance by modeling PN_f in two ways. Extensive experiments show our method achieves state-of-the-art on benchmarks Flickr30K and MSCOCO.

Identification of Necessary Semantic Undertakers in the Causal View for Image-Text Matching

Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning granularity, specifically at the unit of a convolution filter, often leads to undesirable accuracy drops due to the inflexibility of deciding how and where to introduce sparsity to the CNNs. In this paper, we propose REPrune, a novel channel pruning technique that emulates kernel pruning, fully exploiting the finer but structured granularity. REPrune identifies similar kernels within each channel using agglomerative clustering. Then, it selects filters that maximize the incorporation of kernel representatives while optimizing the maximum cluster coverage problem. By integrating with a simultaneous training-pruning paradigm, REPrune promotes efficient, progressive pruning throughout training CNNs, avoiding the conventional train-prune-finetune sequence. Experimental results highlight that REPrune performs better in computer vision tasks than existing methods, effectively achieving a balance between acceleration ratio and performance retention.

REPrune: Channel Pruning via Kernel Representative Selection | VIDEO

Monocular 3D object detection usually adopts direct or hierarchical label supervision. Recently, the distillation supervision transfers the spatial knowledge from LiDAR- or stereo-based teacher networks to monocular detectors, but remaining the domain gap. To mitigate this issue and pursue adequate label manipulation, we exploit Foreground Depth map for feature-supervised monocular 3D object detection named FD3D, which develops the high-quality instructive intermediate features to conduct desirable auxiliary feature supervision with only the original image and annotation foreground object-wise depth map (AFOD) as input. Furthermore, we build up our instructive feature generation network to create instructive spatial features based on the sufficient correlation between image features and pre-processed AFOD, where AFOD provides the attention focus only on foreground objects to achieve clearer guidance in the detection task. Moreover, we apply the auxiliary feature supervision from the pixel and distribution level to achieve comprehensive spatial knowledge guidance. Extensive experiments demonstrate that our method achieves state-of-the-art performance on both the KITTI and nuScenes datasets, with no external data and no extra inference computational cost. We also conduct quantitative and qualitative studies to reveal the effectiveness of our designs.

FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection | VIDEO

Deep implicit functions (DIFs) have emerged as a potent and articulate means of representing 3D shapes. However, methods modeling object categories or non-rigid entities have mainly focused on single-object scenarios. In this work, we propose MODIF, a multi-object deep implicit function that jointly learns the deformation fields and instance-specific latent codes for multiple objects at once. Our emphasis is on non-rigid, non-interpenetrating entities such as organs. To effectively capture the interrelation between these entities and ensure precise, collision-free representations, our approach facilitates signaling between category-specific fields to adequately rectify shapes. We also introduce novel inter-object supervision: an attraction-repulsion loss is formulated to refine contact regions between objects. Our approach is demonstrated on various medical benchmarks, involving modeling different groups of intricate anatomical entities. Experimental results illustrate that our model can proficiently learn the shape representation of each organ and their relations to others, to the point that shapes missing from unseen instances can be consistently recovered by our method. Finally, MODIF can also propagate semantic information throughout the population via accurate point correspondences

Implicit Modeling of Non-rigid Objects with Cross-Category Signals

Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately such anomalies requires models to reason about various component types through segmentation. However, curation of pixel-level annotations for semantic segmentation is both time-consuming and expensive. Although there are some prior few-shot or unsupervised co-part segmentation algorithms, they often fail on images with industrial object. These images have components with similar textures and shapes, and a precise differentiation proves challenging. In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints. To ensure consistent segmentation across unlabeled images, we employ a histogram matching loss in conjunction with an entropy loss. As segmentation predictions play a crucial role, we propose to enhance both local and global sample validity detection by capturing key aspects from visual semantics via three memory banks: class histograms, component composition embeddings and patch-level representations. For effective LA detection, we propose an adaptive scaling strategy to standardize anomaly scores from different memory banks in inference. Extensive experiments on the public benchmark MVTec LOCO AD reveal our method achieves 98.1% AUROC in LA detection vs. 89.6% from competing methods.

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection | VIDEO

Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specific domains, like remote sensing images (RSIs), medical images, etc, remains unexplored and challenging. Existing prompt learning methods often lack domain-awareness or domain-transfer mechanisms, leading to suboptimal performance due to the misinterpretation of specific images in natural image patterns.  To tackle this dilemma, we proposed a Domain-Controlled Prompt Learning for the specific domains. Specifically, the large-scale specific domain foundation model (LSDM) is first introduced to provide essential specific domain knowledge. Using lightweight neural networks, we transfer this knowledge into domain biases, which control both the visual and language branches to obtain domain-adaptive prompts in a directly incorporating manner.  Simultaneously, to overcome the existing overfitting challenge, we propose a novel noisy-adding strategy, without extra trainable parameters, to help the model escape the suboptimal solution in a global domain oscillation manner. Experimental results show our method achieves state-of-the-art performance in specific domain image recognition datasets. Our code is available at https://github.com/caoql98/DCPL.

Content not yet available

Curved Representation Space of Vision Transformers

Downloads

Next from AAAI 2024

SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting | VIDEO

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

Curved Representation Space of Vision Transformers

.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

SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting | VIDEO

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads