Related papers: Augmenting Proposals by the Detector Itself

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

We present a generic and flexible module that encodes region proposals by both their intrinsic features and the extrinsic correlations to the others. The proposed non-local region of interest (NL-RoI) can be seamlessly adapted into…

Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on…

Region proposal based methods like R-CNN and Faster R-CNN models have proven to be extremely successful in object detection and segmentation tasks. Recently, Transformers have also gained popularity in the domain of Computer Vision, and are…

Many recently developed object detectors focused on coarse-to-fine framework which contains several stages that classify and regress proposals from coarse-grain to fine-grain, and obtains more accurate detection gradually. Multi-resolution…

Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms. In this paper, we describe a robust adversarial perturbation (R-AP) method to attack deep proposal-based object detectors and…

Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts.…

Image representations derived from pre-trained Convolutional Neural Networks (CNNs) have become the new state of the art in computer vision tasks such as instance retrieval. This work explores the suitability for instance retrieval of…

Despite the increasing development of Artificial Intelligence (AI) systems, Requirements Engineering (RE) activities face challenges in this new data-intensive paradigm. We identified a lack of support for problem discovery within AI…

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple…

Query optimization is a crucial component for the efficacy of Retrieval-Augmented Generation (RAG) systems. While reinforcement learning (RL)-based agentic and reasoning methods have recently emerged as a promising direction on query…

Recently, action proposal methods have played an important role in action recognition tasks, as they reduce the search space dramatically. Most unsupervised action proposal methods tend to generate hundreds of action proposals which include…

Self-attention is one of the most successful designs in deep learning, which calculates the similarity of different tokens and reconstructs the feature based on the attention matrix. Originally designed for NLP, self-attention is also…

Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows…

Modern large-scale recommender systems employ multi-stage ranking funnel (Retrieval, Pre-ranking, Ranking) to balance engagement and computational constraints (latency, CPU). However, the initial retrieval stage, often relying on efficient…

Developers often need to use appropriate APIs to program efficiently, but it is usually a difficult task to identify the exact one they need from a vast of candidates. To ease the burden, a multitude of API recommendation approaches have…

Object proposals greatly benefit object detection task in recent state-of-the-art works. However, the existing object proposals usually have low localization accuracy at high intersection over union threshold. To address it, we apply…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding…

Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depends on the localization accuracy of a pedestrian detector.…