相关论文: ASAG: Building Strong One-Decoder-Layer Sparse Det…

Compressed sensing (CS) provides an elegant framework for recovering sparse signals from compressed measurements. For example, CS can exploit the structure of natural images and recover an image from only a few random measurements. CS is…

Deep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many AI fields. Adversarial attack is a method that causes the intended misclassfication by adding imperceptible perturbations to…

In light of their capability to capture structural information while reducing computing complexity, anchor graph-based multi-view clustering (AGMC) methods have attracted considerable attention in large-scale clustering problems.…

Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment…

The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance. However, these methods still struggle at large-scale and viewpoint variations, due to the geometric inconsistency…

Cooperative perception can increase the view field and decrease the occlusion of an ego vehicle, hence improving the perception performance and safety of autonomous driving. Despite the success of previous works on cooperative object…

Synthetic data generation to improve classification performance (data augmentation) is a well-studied problem. Recently, generative adversarial networks (GAN) have shown superior image data augmentation performance, but their suitability in…

In recent years, hardware implementations of Ising machines have emerged as a viable alternative to quantum computing for solving hard optimization problems among other applications. Unlike quantum hardware, dense connectivity can be…

The paper addresses challenges in storing and retrieving sequences in contexts like anomaly detection, behavior prediction, and genetic information analysis. Associative Knowledge Graphs (AKGs) offer a promising approach by leveraging…

Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively…

Sparse superposition codes were recently introduced by Barron and Joseph for reliable communication over the AWGN channel at rates approaching the channel capacity. The codebook is defined in terms of a Gaussian design matrix, and codewords…

Existing pseudo label generation methods for point weakly supervised object detection are inadequate in low data volume and dense object detection tasks. We consider the generation of weakly supervised pseudo labels as the model's sparse…

For the additive white Gaussian noise channel with average codeword power constraint, sparse superposition codes are developed. These codes are based on the statistical high-dimensional regression framework. The paper [IEEE Trans. Inform.…

Tensor accelerators have gained popularity because they provide a cheap and efficient solution for speeding up computational-expensive tasks in Deep Learning and, more recently, in other Scientific Computing applications. However, since…

Wireless OFDM channels can be approximated by a time varying filter with sparse time domain taps. Recent achievements in sparse signal processing such as compressed sensing have facilitated the use of sparsity in estimation, which improves…

Traditional object detectors employ the dense paradigm of scanning over locations and scales in an image. The recent query-based object detectors break this convention by decoding image features with a set of learnable queries. However,…

Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a…

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

We revisit the problem of training attention-based sparse image matching models for various local features. We first identify one critical design choice that has been previously overlooked, which significantly impacts the performance of the…

To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a…