Related papers: Gen-n-Val: Agentic Image Data Generation and Valid…

Scaling up the vocabulary of semantic segmentation models is extremely challenging because annotating large-scale mask labels is labour-intensive and time-consuming. Recently, language-guided segmentation models have been proposed to…

Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance. While recent vision language models (VLMs) alleviate…

Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the diversity and heterogeneity of tasks and modalities. A promising…

Fine-grained classification remains a challenging task because distinguishing categories needs learning complex and local differences. Diversity in the pose, scale, and position of objects in an image makes the problem even more difficult.…

Detecting AI-synthetic faces presents a critical challenge: it is hard to capture consistent structural relationships between facial regions across diverse generation techniques. Current methods, which focus on specific artifacts rather…

We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens…

Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they…

Vision-Language Models (VLMs) have shown strong performance in zero-shot image classification tasks. However, existing methods, including Contrastive Language-Image Pre-training (CLIP), all rely on annotated text-to-image pairs for aligning…

Multimodal Large Language Models (MLLMs) have achieved strong performance on general visual benchmarks but struggle with out-of-distribution (OOD) tasks in specialized domains such as medical imaging, where labeled data is limited and…

Despite the previous success of object analysis, detecting and segmenting a large number of object categories with a long-tailed data distribution remains a challenging problem and is less investigated. For a large-vocabulary classifier,…

In recent years, AI-generated videos have become increasingly realistic and sophisticated. Meanwhile, Large Vision-Language Models (LVLMs) have shown strong potential for detecting such content. However, existing evaluation protocols…

Referring image segmentation (RIS) aims to segment an object mentioned in natural language from an image. The main challenge is text-to-pixel fine-grained correlation. In the previous methods, the final results are obtained by convolutions…

In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availability of training data to mitigate quantization errors, a…

Vision-Language Models (VLMs) have recently emerged, demonstrating remarkable vision-understanding capabilities. However, training these models requires large-scale datasets, which brings challenges related to efficiency, effectiveness, and…

The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators…

Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant…

Unsupervised image translation, which aims in translating two independent sets of images, is challenging in discovering the correct correspondences without paired data. Existing works build upon Generative Adversarial Network (GAN) such…

Ensuring the security of complex system-on-chips (SoCs) designs is a critical imperative, yet traditional verification techniques struggle to keep pace due to significant challenges in automation, scalability, comprehensiveness, and…

Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we…

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…