Related papers: BEM: Training-Free Background Embedding Memory for…

Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external storage require complex management and incur storage overhead,…

Energy-based models (EBMs) have become increasingly popular within computer vision in recent years. While they are commonly employed for generative image modeling, recent work has applied EBMs also for regression tasks, achieving…

Tiny object detection (TOD) reveals a fundamental flaw in feature pyramid networks: high-level features (P5-P6) frequently receive zero positive anchors under standard label assignment protocols, leaving their semantic representations…

This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embedding Optimization (PEO), leverages a pre-trained text-to-image…

The Common Objects in Context (COCO) dataset has been instrumental in benchmarking object detectors over the past decade. Like every dataset, COCO contains subtle errors and imperfections stemming from its annotation procedure. With the…

Training implicit neural representations (INRs) to capture fine-scale details typically relies on iterative backpropagation and is often hindered by spectral bias when the target exhibits highly non-uniform frequency content. We propose…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…

Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this…

To handle the complexities of real-world traffic, learning planners for self-driving from data is a promising direction. While recent approaches have shown great progress, they typically assume a setting in which the ground-truth world…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

In text-to-image (T2I) generation applications, negative embeddings have proven to be a simple yet effective approach for enhancing generation quality. Typically, these negative embeddings are derived from user-defined negative prompts,…

Object detection aims to identify instances of semantic objects of a certain class in images or videos. The success of state-of-the-art approaches is attributed to the significant progress of object proposal and convolutional neural…

Bi-CamoDiffusion is introduced, an evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-stage embeddings via a parameter-free injection process, which enhances boundary sharpness…

Malware is becoming increasingly complex and widespread, making it essential to develop more effective and timely detection methods. Traditional static analysis often fails to defend against modern threats that employ code obfuscation,…

We introduce Corrupted Image Modeling (CIM) for self-supervised visual pre-training. CIM uses an auxiliary generator with a small trainable BEiT to corrupt the input image instead of using artificial [MASK] tokens, where some patches are…

Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional…

Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity. Active learning is one way to address the challenge of scarce labeled data in practice, by dynamically collecting the…

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…

Current open-source Large Multimodal Models (LMMs) excel at tasks such as open-vocabulary language grounding and segmentation but can suffer under false premises when queries imply the existence of something that is not actually present in…