Related papers: Low-rank Orthogonal Subspace Intervention for Gene…

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization…

The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem…

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane…

With the rapid development of facial manipulation techniques, face forgery has received considerable attention in multimedia and computer vision community due to security concerns. Existing methods are mostly designed for single-frame…

The surge in face forgeries has increasingly undermined confidence in the authenticity of online content. As generation algorithms rapidly evolve, new fake categories will constantly emerge, severely challenging existing face forgery…

Previous deepfake detection methods mostly depend on low-level textural features vulnerable to perturbations and fall short of detecting unseen forgery methods. In contrast, high-level semantic features are less susceptible to perturbations…

Unsupervised Federated Learning (UFL) aims to collaboratively train a global model across distributed clients without sharing data or accessing label information. Previous UFL works have predominantly focused on representation learning and…

With the rapid development of facial manipulation techniques, face forgery detection has received considerable attention in digital media forensics due to security concerns. Most existing methods formulate face forgery detection as a…

Vision-Language (V-L) pre-trained models such as CLIP show prominent capabilities in various downstream tasks. Despite this promise, V-L models are notoriously limited by their inherent social biases. A typical demonstration is that V-L…

Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical issues with LS. First, LS induces overconfidence in…

We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small…

Synthetic datasets are often used to pretrain end-to-end optical flow networks, due to the lack of a large amount of labeled, real-scene data. But major drops in accuracy occur when moving from synthetic to real scenes. How do we better…

Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in many regions. While contrastive learning methods show…

Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet previously underexplored class of hallucinations driven…

Representational similarity analysis (RSA) is a multivariate technique to investigate cortical representations of objects or constructs. While avoiding ill-posed matrix inversions that plague multivariate approaches in the presence of many…

Recently, Large Vision-Language Models (LVLMs) show remarkable performance across various domains. However, these models suffer from object hallucination. In this work, we study object hallucination primarily in a discriminative,…

Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all…

The rapid advancement of generative models has increased the demand for generated image detectors capable of generalizing across diverse and evolving generation techniques. However, existing methods, including those leveraging pre-trained…

Fine-grained anomaly detection is crucial in industrial and medical applications, but labeled anomalies are often scarce, making zero-shot detection challenging. While vision-language models like CLIP offer promising solutions, they…

Few-shot adaptation of vision-language models remains fundamentally limited by how negative class signals are handled at inference. Existing methods apply uniform negative suppression across all queries, ignoring that the most damaging…