相关论文: AGC: Adaptive Geodesic Correction for Adversarial …

Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has explored robust text prompts through adversarial training,…

LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak…

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…

Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by…

For dynamic visible light communication (VLC) systems, received optical power fluctuates largely due to the fast movement of VLC terminals. Such fluctuations will cause possible signal clipping and quantization noise at the…

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…

Understanding the representation shift on Vision Language Models like CLIP under different augmentations provides valuable insights on Mechanistic Interpretability. In this study, we show the shift on CLIP's embeddings on 9 common…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, introducing a framework…

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…

Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits…

Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology. However, fine-tuning billions of parameters on scarce, expert-annotated pathology data…

Training large language models (LLMs) presents numerous challenges, including gradient instability and loss spikes. These phenomena can lead to catastrophic divergence, requiring costly checkpoint restoration and data batch skipping.…

Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and…

Multimodal contrastive learning aims to train a general-purpose feature extractor, such as CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit various complex downstream tasks, including cross-modal…

Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

Contrastive vision-language models (e.g. CLIP) are typically created by updating all the parameters of a vision model and language model through contrastive training. Can such models be created by a small number of parameter updates to an…

Zero-shot anomaly detection (ZSAD) enables anomaly detection without normal samples from target categories, addressing scenarios where task-specific training data is unavailable. However, existing ZSAD methods either neglect adaptation of…

There are many recent research efforts to fine-tune a pre-trained generator with a few target images to generate images of a novel domain. Unfortunately, these methods often suffer from overfitting or under-fitting when fine-tuned with a…