相关论文: Multiscale Feature Importance-based Bit Allocation…

Vision-Language Models (VLMs) have shown strong capabilities on diverse multimodal tasks. However, the large number of visual tokens output by the vision encoder severely hinders inference efficiency, and prior studies have shown that many…

Camouflaged Object Detection (COD) is challenging due to the strong similarity between camouflaged objects and their surroundings, which complicates identification. Existing methods mainly rely on spatial local features, failing to capture…

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification. This is done by means of a three-step methodology that involves (i) building a classifier and tuning its…

Mainstream image and video coding standards -- including state-of-the-art codecs like H.266/VVC, AVS3, and AV1 -- adopt a block-based hybrid coding framework. While this framework facilitates straightforward optimization for Peak…

Fine-grained visual classification is a challenging task that recognizes the sub-classes belonging to the same meta-class. Large inter-class similarity and intra-class variance is the main challenge of this task. Most exiting methods try to…

Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the…

With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the predominant inference…

We present a new image compression paradigm to achieve ``intelligently coding for machine'' by cleverly leveraging the common sense of Large Multimodal Models (LMMs). We are motivated by the evidence that large language/multimodal models…

Deep learning-based methods have achieved promising results on surgical instrument segmentation. However, the high computation cost may limit the application of deep models to time-sensitive tasks such as online surgical video analysis for…

Bit-flipping (BF) decoding of low-density parity-check codes is of low complexity but gives inferior performance in general. To improve performance and provide new BF decoder options for complexity-performance tradeoffs, we propose new…

A promising way to deploy Artificial Intelligence (AI)-based services on mobile devices is to run a part of the AI model (a deep neural network) on the mobile itself, and the rest in the cloud. This is sometimes referred to as collaborative…

Applications of Fully Convolutional Networks (FCN) in iris segmentation have shown promising advances. For mobile and embedded systems, a significant challenge is that the proposed FCN architectures are extremely computationally demanding.…

The feature attribution method reveals the contribution of input variables to the decision-making process to provide an attribution map for explanation. Existing methods grounded on the information bottleneck principle compute information…

The integral image, an intermediate image representation, has found extensive use in multi-scale local feature detection algorithms, such as Speeded-Up Robust Features (SURF), allowing fast computation of rectangular features at constant…

An increasing share of captured images and videos are transmitted for storage and remote analysis by computer vision algorithms, rather than to be viewed by humans. Contrary to traditional standard codecs with engineered tools, neural…

Integrating high-level context information with low-level details is of central importance in semantic segmentation. Towards this end, most existing segmentation models apply bilinear up-sampling and convolutions to feature maps of…

In this paper, we propose a novel end-to-end feature compression scheme by leveraging the representation and learning capability of deep neural networks, towards intelligent front-end equipped analysis with promising accuracy and…

Scalable image compression is a technique that progressively reconstructs multiple versions of an image for different requirements. In recent years, images have increasingly been consumed not only by humans but also by image recognition…

This paper presents an open-source Python toolbox called Ensemble Feature Importance (EFI) to provide machine learning (ML) researchers, domain experts, and decision makers with robust and accurate feature importance quantification and more…