Related papers: Redundant Queries in DETR-Based 3D Detection Metho…

Query-based methods with dense features have demonstrated remarkable success in 3D object detection tasks. However, the computational demands of these models, particularly with large image sizes and multiple transformer layers, pose…

A large item catalogue is a major challenge for deploying modern sequential recommender models, since it makes the memory footprint of the model large and increases inference latency. One promising approach to address this is RecJPQ, which…

In this paper, we propose an efficient feature pruning strategy for 3D small object detection. Conventional 3D object detection methods struggle on small objects due to the weak geometric information from a small number of points. Although…

To reduce computational overhead while maintaining model performance, model pruning techniques have been proposed. Among these, structured pruning, which removes entire convolutional channels or layers, significantly enhances computational…

Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by…

The query mechanism introduced in the DETR method is changing the paradigm of object detection and recently there are many query-based methods have obtained strong object detection performance. However, the current query-based detection…

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…

Recent advances in dense retrieval techniques have offered the promise of being able not just to re-rank documents using contextualised language models such as BERT, but also to use such models to identify documents from the collection in…

Learning implicit representations has been a widely used solution for surface reconstruction from 3D point clouds. The latest methods infer a distance or occupancy field by overfitting a neural network on a single point cloud. However,…

Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual query tokens directly to image patches and achieving state-of-the-art performance on public benchmarks. Recent models relying on this paradigm…

End-to-end object detection is rapidly progressed after the emergence of DETR. DETRs use a set of sparse queries that replace the dense candidate boxes in most traditional detectors. In comparison, the sparse queries cannot guarantee a high…

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR…

Applying deep neural networks to 3D point cloud processing has attracted increasing attention due to its advanced performance in many areas, such as AR/VR, autonomous driving, and robotics. However, as neural network models and 3D point…

We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. In contrast to weight or filter-level pruning, layer pruning reduces the harder to parallelize…

We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. To…

Recent advances in novel view synthesis have enabled real-time rendering speeds with high reconstruction accuracy. 3D Gaussian Splatting (3D-GS), a foundational point-based parametric 3D scene representation, models scenes as large sets of…

Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…

This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them…

One-to-one label assignment in object detection has successfully obviated the need for non-maximum suppression (NMS) as postprocessing and makes the pipeline end-to-end. However, it triggers a new dilemma as the widely used sparse queries…