Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data for training CNN-based intrinsic image decomposition models, then app...
Anomaly detection aims at identifying images that deviate significantly from the norm. We focus on algorithms that embed the normal training examples in space and when given a test image, detect anomalies based on the features distance to the k-neare...
Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most existing approach...
IT-Online. Retrieved 19 February 2026. "CompTIA honours training partners". Channelwise. Retrieved 19 February 2026. Sunday Times GenNext 2022 winners (PDF)
May 1, 2025 · One common approach is training models to refuse unsafe queries, but this strategy can be vulnerable to clever prompts, often referred to as jailbreak attacks, which can trick the AI into …
Many modern machine learning algorithms such as generative adversarial networks (GANs) and adversarial training can be formulated as minimax optimization. Gradient descent ascent (GDA) is the most commonly used algorithm due to its simplicity. Howeve...
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging...
In practice, the hyperparameters $(β_1, β_2)$ and weight-decay $λ$ in AdamW are typically kept at fixed values. Is there any reason to do otherwise? We show that for large-scale language model training, the answer is yes: by exploiting the power-l...
GUI for marking bounded boxes of objects in images for training neural network Yolo v3 and v2 (⭐ 1847)
The article is devoted to the rationale of the use of cloud technologies in teaching mathematical informatics students of technical universities. Purpose of the article - the analysis of domestic and foreign experience in the use of cloud-oriented IC...
A professional is a member of a profession or any person who works in a specified professional activity. The term also describes the standards of education and training that prepare members of the …
Ongoing research training transformer models at scale (⭐ 15534)
We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intend...
[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 resolution)…
Full version (training+testing) of implementation of Shizhan Zhu et al.'s ICCV-17 work Be Your Own Prada: Fashion Synthesis with Structural Coherence (⭐ 371)
Dec 11, 2025 · Learn how to prepare for an interview with interview prep questions, tips and tactics and how to get started with AI-powered interview training.
Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches require a...
Mitigating the dependence on spurious correlations present in the training dataset is a quickly emerging and important topic of deep learning. Recent approaches include priors on the feature attribution of a deep neural network (DNN) into the trainin...
Large language models (LLMs) are increasingly used for long-document question answering, where reliable attribution to sources is critical for trust. Existing post-hoc attribution methods work well for extractive QA but struggle in multi-hop, abstrac...
Dataset distillation synthesizes a small set of images from a large-scale real dataset such that synthetic and real images share similar behavioral properties (e.g, distributions of gradients or features) during a training process. Through extensive...