Related papers: LiteGuard: Efficient Task-Agnostic Model Fingerpri…
To benefit the learning of a new task, meta-learning has been proposed to transfer a well-generalized meta-model learned from various meta-training tasks. Existing meta-learning algorithms randomly sample meta-training tasks with a uniform…
Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…
A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we learn an optimal model in training data, it could have better generalization performance in testing tasks. However, learning such a…
Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and…
Face recognition has achieved unprecedented results, surpassing human capabilities in certain scenarios. However, these automatic solutions are not ready for production because they can be easily fooled by simple identity impersonation…
Long-tailed semi-supervised learning (LTSSL) presents a formidable challenge where models must overcome the scarcity of tail samples while mitigating the noise from unreliable pseudo-labels. Most prior LTSSL methods are designed to train…
Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot recognition, image generation & editing, and many other…
Growing amount of different practical tasks in a video understanding problem has addressed the great challenge aiming to design an universal solution, which should be available for broad masses and suitable for the demanding edge-oriented…
Parameter-efficient fine-tuning (PEFT) has attracted significant attention due to the growth of pre-trained model sizes and the need to fine-tune (FT) them for superior downstream performance. Despite a surge in new PEFT methods, a…
Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e.g., GPUs) or require the collection of specific training data. Instead, it involves editing different upstream model…
Large language models show impressive results on few-shot NLP tasks. However, these models are memory and computation-intensive. Meta-training allows one to leverage smaller models for few-shot generalization in a domain-general and…
Deep learning models for image classification have become standard tools in recent years. A well known vulnerability of these models is their susceptibility to adversarial examples. These are generated by slightly altering an image of a…
Recent advanced methods for fashion landmark detection are mainly driven by training convolutional neural networks on large-scale fashion datasets, which has a large number of annotated landmarks. However, such large-scale annotations are…
Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked…
Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a…
As a general-purpose vision-language pretraining model, CLIP demonstrates strong generalization ability in image-text alignment tasks and has been widely adopted in downstream applications such as image classification and image-text…
Fingerprint verification systems are becoming ubiquitous in everyday life. This trend is propelled especially by the proliferation of mobile devices with fingerprint sensors such as smartphones and tablet computers, and fingerprint…
The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by information loss and poor…
In real-world scenarios, it may not always be possible to collect hundreds of labeled samples per class for training deep learning-based SAR Automatic Target Recognition (ATR) models. This work specifically tackles the few-shot SAR ATR…
Image generation algorithms are increasingly integral to diverse aspects of human society, driven by their practical applications. However, insufficient oversight in artificial Intelligence generated content (AIGC) can facilitate the spread…