相关论文: Masked Jigsaw Puzzle: A Versatile Position Embeddi…

Model inversion is a widely adopted technique in data-free learning that reconstructs synthetic inputs from a pretrained model through iterative optimization, without access to original training data. Unfortunately, its application to…

LiDAR sensors are widely used in autonomous vehicles to better perceive the environment. However, prior works have shown that LiDAR signals can be spoofed to hide real objects from 3D object detectors. This study explores the feasibility of…

Diffusion Transformers (DiTs) have emerged as the dominant architecture for visual generation, powering state-of-the-art image and video models. By representing images as patch tokens with positional encodings (PEs), DiTs combine…

In the task of image classification, usually, the network is sensitive to noises. For example, an image of cat with noises might be misclassified as an ostrich. Conventionally, to overcome the problem of noises, one uses the technique of…

How can multiple distributed entities collaboratively train a shared deep net on their private data while preserving privacy? This paper introduces InstaHide, a simple encryption of training images, which can be plugged into existing…

Sparse query-based paradigms have achieved significant success in multi-view 3D detection for autonomous vehicles. Current research faces challenges in balancing between enlarging receptive fields and reducing interference when aggregating…

Self-supervised pre-training vision transformer (ViT) via masked image modeling (MIM) has been proven very effective. However, customized algorithms should be carefully designed for the hierarchical ViTs, e.g., GreenMIM, instead of using…

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

Current methods for detecting spurious correlations rely on analyzing dataset statistics or error patterns, leaving many harmful shortcuts invisible when counterexamples are absent. We introduce BEE (Bridging Explainability and Embeddings),…

We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we…

The projected entangled pair states (PEPS) methods have been proved to be powerful tools to solve the strongly correlated quantum many-body problems in two-dimension. However, due to the high computational scaling with the virtual bond…

Pixel Value Ordering (PVO) holds an impressive property for high fidelity Reversible Data Hiding (RDH). In this paper, we introduce a dual-PVO (dPVO) for Prediction Error Expansion(PEE), and thereby develop a new RDH scheme to offer a…

Federated learning reduces the risk of information leakage, but remains vulnerable to attacks. We investigate how several neural network design decisions can defend against gradients inversion attacks. We show that overlapping gradients…

As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident. To…

The growth of open-source software has increased the risk of hidden vulnerabilities that can affect downstream software applications. This concern is further exacerbated by software vendors' practice of silently releasing security patches…

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…

Recurrent models have been dominating the field of neural machine translation (NMT) for the past few years. Transformers \citep{vaswani2017attention}, have radically changed it by proposing a novel architecture that relies on a feed-forward…

As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry. However, its security is constantly being questioned since the intermediate results are shared during training and…

Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's…

In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…