Related papers: Towards Universal Image Embeddings: A Large-Scale …
Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural…
Few-shot deep learning is a topical challenge area for scaling visual recognition to open ended growth of unseen new classes with limited labeled examples. A promising approach is based on metric learning, which trains a deep embedding to…
Image classification has advanced significantly in recent years with the availability of large-scale image sets. However, fine-grained classification remains a major challenge due to the annotation cost of large numbers of fine-grained…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…
Visible images offer rich texture details, while infrared images emphasize salient targets. Fusing these complementary modalities enhances scene understanding, particularly for advanced vision tasks under challenging conditions. Recently,…
Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where…
The generalization capability of neural networks across domains is crucial for real-world applications. We argue that a generalized object recognition system should well understand the relationships among different images and also the…
Ensembling is a successful technique to improve the performance of machine learning (ML) models. Conf-Ensemble is an adaptation to Boosting to create ensembles based on model confidence instead of model errors to better classify difficult…
The widespread adoption of whole slide imaging has increased the demand for effective and efficient gigapixel image analysis. Deep learning is at the forefront of computer vision, showcasing significant improvements over previous…
Global localisation from visual data is a challenging problem applicable to many robotics domains. Prior works have shown that neural networks can be trained to map images of an environment to absolute camera pose within that environment,…
Zooplankton images, like many other real world data types, have intrinsic properties that make the design of effective classification systems difficult. For instance, the number of classes encountered in practical settings is potentially…
The astounding success made by artificial intelligence (AI) in healthcare and other fields proves that AI can achieve human-like performance. However, success always comes with challenges. Deep learning algorithms are data-dependent and…
Advances in object recognition flourished in part because of the availability of high-quality datasets and associated benchmarks. However, these benchmarks---such as ILSVRC---are relatively task-specific, focusing predominately on…
Despite the breakthroughs achieved by deep learning models in conventional supervised learning scenarios, their dependence on sufficient labeled training data in each class prevents effective applications of these deep models in situations…
Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight…
IMPORTANCE: Modern ultrasound systems are universal diagnostic tools capable of imaging the entire body. However, current AI solutions remain fragmented into single-task tools. This critical gap between hardware versatility and software…
Facial Expression Recognition is a commercially-important application, but one under-appreciated limitation is that such applications require making predictions on out-of-sample distributions, where target images have different properties…
Foundation models (FMs) have emerged as a transformative paradigm in medical image analysis, offering the potential to provide generalizable, task-agnostic solutions across a wide range of clinical tasks and imaging modalities. Their…
Two questions regarding practitioners' use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other…
Historical watermark recognition is a highly practical, yet unsolved challenge for archivists and historians. With a large number of well-defined classes, cluttered and noisy samples, different types of representations, both subtle…