Related papers: BEM: Training-Free Background Embedding Memory for…
Estimating the depth of objects from a single image is a valuable task for many vision, robotics, and graphics applications. However, current methods often fail to produce accurate depth for objects in diverse scenes. In this work, we…
Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…
Function names can greatly aid human reverse engineers, which has spurred the development of machine learning-based approaches to predicting function names in stripped binaries. Much current work in this area now uses transformers, applying…
Foundation models, especially vision-language models (VLMs), offer compelling zero-shot object detection for applications like autonomous driving, a domain where manual labelling is prohibitively expensive. However, their detection latency…
As repositories of large scale data in earth observation (EO) have grown, so have transfer and storage costs for model training and inference, expending significant resources. We introduce Neural Embedding Compression (NEC), based on the…
Entity Matching (EM)--the task of determining whether two data records refer to the same real-world entity--is a core task in data integration. Recent advances in deep learning have set a new standard for EM, particularly through…
Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate…
Model ensemble is a popular approach to produce a low-variance and well-generalized model. However, it induces large memory and inference costs, which are often not affordable for real-world deployment. Existing work has resorted to sharing…
Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these positively labeled…
World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context window often leads to failures in maintaining long-term…
Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…
In recent years, the demand of image compression models for machine vision has increased dramatically. However, the training frameworks of image compression still focus on the vision of human, maintaining the excessive perceptual details,…
While Large Vision-Language Models (LVLMs) offer powerful capabilities, they pose privacy risks by unintentionally memorizing sensitive personal information. Current unlearning benchmarks attempt to mitigate this using fictitious identities…
Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method…
We present YOLOBench, a benchmark comprised of 550+ YOLO-based object detection models on 4 different datasets and 4 different embedded hardware platforms (x86 CPU, ARM CPU, Nvidia GPU, NPU). We collect accuracy and latency numbers for a…
Recent feature matching methods have achieved remarkable performance but lack efficiency consideration. In this paper, we revisit the mainstream detector-free matching pipeline and improve all its stages considering both accuracy and…
Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work,…
We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR). To mitigate the sparse supervision inherent in one-to-one (O2O)…
The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…
Deep learning-based methods for low-light image enhancement typically require enormous paired training data, which are impractical to capture in real-world scenarios. Recently, unsupervised approaches have been explored to eliminate the…