Related papers: Learning to Represent Patches
Visual place recognition is a challenging task in the field of computer vision, and autonomous robotics and vehicles, which aims to identify a location or a place from visual inputs. Contemporary methods in visual place recognition employ…
Training a deep learning model on source code has gained significant traction recently. Since such models reason about vectors of numbers, source code needs to be converted to a code representation before vectorization. Numerous approaches…
Some image restoration tasks like demosaicing require difficult training samples to learn effective models. Existing methods attempt to address this data training problem by manually collecting a new training dataset that contains adequate…
Utilizing an abstract information processing model based on minimal yet realistic assumptions inspired by biological systems, we study how to achieve the early visual system's two ultimate objectives: efficient information transmission and…
The recent rise of generative artificial intelligence (AI), powered by Transformer networks, has achieved remarkable success in natural language processing, computer vision, and graphics. However, the application of Transformers in…
Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization. Prevailing paradigms, however, present a dilemma. Static…
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal. While these…
Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads to a loss of…
Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this paper, we…
Understanding search queries is critical for shopping search engines to deliver a satisfying customer experience. Popular shopping search engines receive billions of unique queries yearly, each of which can depict any of hundreds of user…
Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly…
Representations pervade our daily experience, from letters representing sounds to bit strings encoding digital files. While such representations require externally defined decoders to convey meaning, conscious experience appears…
Understanding linguistics and morphology of resource-scarce code-mixed texts remains a key challenge in text processing. Although word embedding comes in handy to support downstream tasks for low-resource languages, there are plenty of…
Line art colorization plays a crucial role in hand-drawn animation production, where digital artists manually colorize segments using a paint bucket tool, guided by RGB values from character color design sheets. This process, often called…
Existing approaches to Implicit Neural Representation (INR) can be interpreted as a global scene representation via a linear combination of Fourier bases of different frequencies. However, such universal basis functions can limit the…
Capturing the long-range dependencies has empirically proven to be effective on a wide range of computer vision tasks. The progressive advances on this topic have been made through the employment of the transformer framework with the help…
Sequence models such as transformers require inputs to be represented as one-dimensional sequences. In vision, this typically involves flattening images using a fixed row-major (raster-scan) order. While full self-attention is…
Transformer models gain popularity because of their superior inference accuracy and inference throughput. However, the transformer is computation-intensive, causing a long inference time. The existing works on transformer inference…
The adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a restricted image region (i.e., a patch) for inducing model misclassification. This attack can be realized in the physical…
In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…