Yang Li

Li Yang, Yan Xu, Chunfeng Yuan et al.

Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They base the visual grounding on the features from pre-generated proposals or anchors, and fuse these features with the text embeddings to locate the target mentioned by the text. However, modeling the visual features from these predefined locations may fail to fully exploit the visual context and attribute information in the text query, which limits their performance. In this paper, we propose a transformer-based framework for accurate visual grounding by establishing text-conditioned discriminative features and performing multi-stage cross-modal reasoning. Specifically, we develop a visual-linguistic verification module to focus the visual features on regions relevant to the textual descriptions while suppressing the unrelated areas. A language-guided feature encoder is also devised to aggregate the visual contexts of the target object to improve the object's distinctiveness. To retrieve the target from the encoded visual features, we further propose a multi-stage cross-modal decoder to iteratively speculate on the correlations between the image and text for accurate target localization. Extensive experiments on five widely used datasets validate the efficacy of our proposed components and demonstrate state-of-the-art performance. Our code is public at https://github.com/yangli18/VLTVG.

Yongjae Lee, Li Yang, Deliang Fan

Neural radiance field (NeRF) has shown remarkable performance in generating photo-realistic novel views. Among recent NeRF related research, the approaches that involve the utilization of explicit structures like grids to manage features achieve exceptionally fast training by reducing the complexity of multilayer perceptron (MLP) networks. However, storing features in dense grids demands a substantial amount of memory space, resulting in a notable memory bottleneck within computer system. Consequently, it leads to a significant increase in training times without prior hyper-parameter tuning. To address this issue, in this work, we are the first to propose MF-NeRF, a memory-efficient NeRF framework that employs a Mixed-Feature hash table to improve memory efficiency and reduce training time while maintaining reconstruction quality. Specifically, we first design a mixed-feature hash encoding to adaptively mix part of multi-level feature grids and map it to a single hash table. Following that, in order to obtain the correct index of a grid point, we further develop an index transformation method that transforms indices of an arbitrary level grid to those of a canonical grid. Extensive experiments benchmarking with state-of-the-art Instant-NGP, TensoRF, and DVGO, indicate our MF-NeRF could achieve the fastest training time on the same GPU hardware with similar or even higher reconstruction quality.

Meihua Zhou, Ivan Fung, Li Yang et al.

Due to the enormous population growth of cities in recent years, objects are frequently lost and unclaimed on public transportation, in restaurants, or any other public areas. While services like Find My iPhone can easily identify lost electronic devices, more valuable objects cannot be tracked in an intelligent manner, making it impossible for administrators to reclaim a large number of lost and found items in a timely manner. We present a method that significantly reduces the complexity of searching by comparing previous images of lost and recovered things provided by the owner with photos taken when registered lost and found items are received. In this research, we will primarily design a photo matching network by combining the fine-tuning method of MobileNetv2 with CBAM Attention and using the Internet framework to develop an online lost and found image identification system. Our implementation gets a testing accuracy of 96.8% using only 665.12M GLFOPs and 3.5M training parameters. It can recognize practice images and can be run on a regular laptop.

Li Yang, Mai Xu, Shengxi Li et al.

Blind visual quality assessment (BVQA) on 360{\textdegree} video plays a key role in optimizing immersive multimedia systems. When assessing the quality of 360{\textdegree} video, human tends to perceive its quality degradation from the viewport-based spatial distortion of each spherical frame to motion artifact across adjacent frames, ending with the video-level quality score, i.e., a progressive quality assessment paradigm. However, the existing BVQA approaches for 360{\textdegree} video neglect this paradigm. In this paper, we take into account the progressive paradigm of human perception towards spherical video quality, and thus propose a novel BVQA approach (namely ProVQA) for 360{\textdegree} video via progressively learning from pixels, frames and video. Corresponding to the progressive learning of pixels, frames and video, three sub-nets are designed in our ProVQA approach, i.e., the spherical perception aware quality prediction (SPAQ), motion perception aware quality prediction (MPAQ) and multi-frame temporal non-local (MFTN) sub-nets. The SPAQ sub-net first models the spatial quality degradation based on spherical perception mechanism of human. Then, by exploiting motion cues across adjacent frames, the MPAQ sub-net properly incorporates motion contextual information for quality assessment on 360{\textdegree} video. Finally, the MFTN sub-net aggregates multi-frame quality degradation to yield the final quality score, via exploring long-term quality correlation from multiple frames. The experiments validate that our approach significantly advances the state-of-the-art BVQA performance on 360{\textdegree} video over two datasets, the code of which has been public in \url{https://github.com/yanglixiaoshen/ProVQA.}

Li Yang, Yan Xu, Shaoru Wang et al.

Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different targets, i.e., the object category and boundaries, are generally different. Predicting all these targets from the same grid location thus may lead to sub-optimal results. In this paper, we analyze the suitable inference positions for object category and boundaries, and propose a prediction-target-decoupled detector named PDNet to establish a more flexible detection paradigm. Our PDNet with the prediction decoupling mechanism encodes different targets separately in different locations. A learnable prediction collection module is devised with two sets of dynamic points, i.e., dynamic boundary points and semantic points, to collect and aggregate the predictions from the favorable regions for localization and classification. We adopt a two-step strategy to learn these dynamic point positions, where the prior positions are estimated for different targets first, and the network further predicts residual offsets to the positions with better perceptions of the object properties. Extensive experiments on the MS COCO benchmark demonstrate the effectiveness and efficiency of our method. With a single ResNeXt-64x4d-101-DCN as the backbone, our detector achieves 50.1 AP with single-scale testing, which outperforms the state-of-the-art methods by an appreciable margin under the same experimental settings.Moreover, our detector is highly efficient as a one-stage framework. Our code is public at https://github.com/yangli18/PDNet.

Li Yang, Zhezhi He, Yu Cao et al.

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy and computation complexity (i.e., latency on target hardware) after model deployment, based on dynamic requirements and environments. Such research direction recently draws great attention, where one realization is to train the target DNN through a multiple-term objective function, which consists of cross-entropy terms from multiple sub-nets. Our investigation in this work show that the performance of dynamic inference highly relies on the quality of sub-net sampling. With objective to construct a dynamic DNN and search multiple high quality sub-nets with minimal searching cost, we propose a progressive sub-net searching framework, which is embedded with several effective techniques, including trainable noise ranking, channel group and fine-tuning threshold setting, sub-nets re-selection. The proposed framework empowers the target DNN with better dynamic inference capability, which outperforms prior works on both CIFAR-10 and ImageNet dataset via comprehensive experiments on different network structures. Taken ResNet18 as an example, our proposed method achieves much better dynamic inference accuracy compared with prior popular Universally-Slimmable-Network by 4.4%-maximally and 2.3%-averagely in ImageNet dataset with the same model size.