Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation. In this work, we propose a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background. Overall, this framework can learn more discriminative features progressively while integrating complementary features together in each stage. Without bells and whistles, a single HTC obtains 38.4 and 1.5 improvement over a strong Cascade Mask R-CNN baseline on MSCOCO dataset. Moreover, our overall system achieves 48.6 mask AP on the test-challenge split, ranking 1st in the COCO 2018 Challenge Object Detection Task. Code is available at: https://github.com/open-mmlab/mmdetection.
Ammunition scrap inspection is an essential step in the process of recycling ammunition metal scrap. Most ammunition is composed of a number of components, including case, primer, powder, and projectile. Ammo scrap containing energetics is considered to be potentially dangerous and should be separated before the recycling process. Manually inspecting each piece of scrap is tedious and time-consuming. We have gathered a dataset of ammunition components with the goal of applying artificial intelligence for classifying safe and unsafe scrap pieces automatically. First, two training datasets are manually created from visual and x-ray images of ammo. Second, the x-ray dataset is augmented using the spatial transforms of histogram equalization, averaging, sharpening, power law, and Gaussian blurring in order to compensate for the lack of sufficient training data. Lastly, the representative YOLOv4 object detection method is applied to detect the ammo components and classify the scrap pieces into safe and unsafe classes, respectively. The trained models are tested against unseen data in order to evaluate the performance of the applied method. The experiments demonstrate the feasibility of ammo component detection and classification using deep learning. The datasets and the pre-trained models are available at https://github.com/hadi-ghnd/Scrap-Classification.
This paper addresses the problem of sheet-image-based on-line audio-to-score alignment also known as score following. Drawing inspiration from object detection, a conditional neural network architecture is proposed that directly predicts x,y coordinates of the matching positions in a complete score sheet image at each point in time for a given musical performance. Experiments are conducted on a synthetic polyphonic piano benchmark dataset and the new method is compared to several existing approaches from the literature for sheet-image-based score following as well as an Optical Music Recognition baseline. The proposed approach achieves new state-of-the-art results and furthermore significantly improves the alignment performance on a set of real-world piano recordings by applying Impulse Responses as a data augmentation technique.
The success of deep learning on video Action Recognition (AR) has motivated researchers to progressively promote related tasks from the coarse level to the fine-grained level. Compared with conventional AR which only predicts an action label for the entire video, Temporal Action Detection (TAD) has been investigated for estimating the start and end time for each action in videos. Taking TAD a step further, Spatiotemporal Action Detection (SAD) has been studied for localizing the action both spatially and temporally in videos. However, who performs the action, is generally ignored in SAD, while identifying the actor could also be important. To this end, we propose a novel task, Actor-identified Spatiotemporal Action Detection (ASAD), to bridge the gap between SAD and actor identification. In ASAD, we not only detect the spatiotemporal boundary for instance-level action but also assign the unique ID to each actor. To approach ASAD, Multiple Object Tracking (MOT) and Action Classification (AC) are two fundamental elements. By using MOT, the spatiotemporal boundary of each actor is obtained and assigned to a unique actor identity. By using AC, the action class is estimated within the corresponding spatiotemporal boundary. Since ASAD is a new task, it poses many new challenges that cannot be addressed by existing methods: i) no dataset is specifically created for ASAD, ii) no evaluation metrics are designed for ASAD, iii) current MOT performance is the bottleneck to obtain satisfactory ASAD results. To address those problems, we contribute to i) annotate a new ASAD dataset, ii) propose ASAD evaluation metrics by considering multi-label actions and actor identification, iii) improve the data association strategies in MOT to boost the MOT performance, which leads to better ASAD results. The code is available at https://github.com/fandulu/ASAD.
Visuals captured by high-flying aerial drones are increasingly used to assess biodiversity and animal population dynamics around the globe. Yet, challenging acquisition scenarios and tiny animal depictions in airborne imagery, despite ultra-high resolution cameras, have so far been limiting factors for applying computer vision detectors successfully with high confidence. In this paper, we address the problem for the first time by combining deep object detectors with super-resolution techniques and altitude data. In particular, we show that the integration of a holistic attention network based super-resolution approach and a custom-built altitude data exploitation network into standard recognition pipelines can considerably increase the detection efficacy in real-world settings. We evaluate the system on two public, large aerial-capture animal datasets, SAVMAP and AED. We find that the proposed approach can consistently improve over ablated baselines and the state-of-the-art performance for both datasets. In addition, we provide a systematic analysis of the relationship between animal resolution and detection performance. We conclude that super-resolution and altitude knowledge exploitation techniques can significantly increase benchmarks across settings and, thus, should be used routinely when detecting minutely resolved animals in aerial imagery.
Efficiently and accurately detecting people from 3D point cloud data is of great importance in many robotic and autonomous driving applications. This fundamental perception task is still very challenging due to (i) significant deformations of human body pose and gesture over time and (ii) point cloud sparsity and scarcity for pedestrian class objects. Recent efficient 3D object detection approaches rely on pillar features to detect objects from point cloud data. However, these pillar features do not carry sufficient expressive representations to deal with all the aforementioned challenges in detecting people. To address this shortcoming, we first introduce a stackable Pillar Aware Attention (PAA) module for enhanced pillar features extraction while suppressing noises in the point clouds. By integrating multi-point-channel-pooling, point-wise, channel-wise, and task-aware attention into a simple module, the representation capabilities are boosted while requiring little additional computing resources. We also present Mini-BiFPN, a small yet effective feature network that creates bidirectional information flow and multi-level cross-scale feature fusion to better integrate multi-resolution features. Our proposed framework, namely PiFeNet, has been evaluated on three popular large-scale datasets for 3D pedestrian Detection, i.e. KITTI, JRDB, and nuScenes achieving state-of-the-art (SOTA) performance on KITTI Bird-eye-view (BEV) and JRDB and very competitive performance on nuScenes. Our approach has inference speed of 26 frame-per-second (FPS), making it a real-time detector. The code for our PiFeNet is available at https://github.com/ldtho/PiFeNet.
Prohibited Item detection in X-ray images is one of the most effective security inspection methods.However, differing from natural light images, the unique overlapping phenomena in X-ray images lead to the coupling of foreground and background features, thereby lowering the accuracy of general object detectors.Therefore, we propose a Multi-Class Min-Margin Contrastive Learning (MMCL) method that, by clarifying the category semantic information of content queries under the deformable DETR architecture, aids the model in extracting specific category foreground information from coupled features.Specifically, after grouping content queries by the number of categories, we employ the Multi-Class Inter-Class Exclusion (MIE) loss to push apart content queries from different groups. Concurrently, the Intra-Class Min-Margin Clustering (IMC) loss is utilized to attract content queries within the same group, while ensuring the preservation of necessary disparity. As training, the inherent Hungarian matching of the model progressively strengthens the alignment between each group of queries and the semantic features of their corresponding category of objects. This evolving coherence ensures a deep-seated grasp of category characteristics, consequently bolstering the anti-overlapping detection capabilities of models.MMCL is versatile and can be easily plugged into any deformable DETR-based model with dozens of lines of code. Extensive experiments on the PIXray and OPIXray datasets demonstrate that MMCL significantly enhances the performance of various state-of-the-art models without increasing complexity. The code has been released at https://github.com/anonymity0403/MMCL.
Instrument playing is among the most common scenes in music-related videos, which represent nowadays one of the largest sources of online videos. In order to understand the instrument-playing scenes in the videos, it is important to know what instruments are played, when they are played, and where the playing actions occur in the scene. While audio-based recognition of instruments has been widely studied, the visual aspect of the music instrument playing remains largely unaddressed in the literature. One of the main obstacles is the difficulty in collecting annotated data of the action locations for training-based methods. To address this issue, we propose a weakly-supervised framework to find when and where the instruments are played in the videos. We propose to use two auxiliary models, a sound model and an object model, to provide supervisions for training the instrument-playing action model. The sound model provides temporal supervisions, while the object model provides spatial supervisions. They together can simultaneously provide temporal and spatial supervisions. The resulted model only needs to analyze the visual part of a music video to deduce which, when and where instruments are played. We found that the proposed method significantly improves the localization accuracy. We evaluate the result of the proposed method temporally and spatially on a small dataset (totally 5,400 frames) that we manually annotated.
It has been a long history that most object detection methods obtain objects by using the non-maximum suppression (NMS) and its improved versions like Soft-NMS to remove redundant bounding boxes. We challenge those NMS-based methods from three aspects: 1) The bounding box with highest confidence value may not be the true positive having the biggest overlap with the ground-truth box. 2) Not only suppression is required for redundant boxes, but also confidence enhancement is needed for those true positives. 3) Sorting candidate boxes by confidence values is not necessary so that full parallelism is achievable. In this paper, inspired by belief propagation (BP), we propose the Confidence Propagation Cluster (CP-Cluster) to replace NMS-based methods, which is fully parallelizable as well as better in accuracy. In CP-Cluster, we borrow the message passing mechanism from BP to penalize redundant boxes and enhance true positives simultaneously in an iterative way until convergence. We verified the effectiveness of CP-Cluster by applying it to various mainstream detectors such as FasterRCNN, SSD, FCOS, YOLOv3, YOLOv5, Centernet etc. Experiments on MS COCO show that our plug and play method, without retraining detectors, is able to steadily improve average mAP of all those state-of-the-art models with a clear margin from 0.3 to 1.9 respectively when compared with NMS-based methods.
This paper introduces the first two pixel retrieval benchmarks. Pixel retrieval is segmented instance retrieval. Like semantic segmentation extends classification to the pixel level, pixel retrieval is an extension of image retrieval and offers information about which pixels are related to the query object. In addition to retrieving images for the given query, it helps users quickly identify the query object in true positive images and exclude false positive images by denoting the correlated pixels. Our user study results show pixel-level annotation can significantly improve the user experience. Compared with semantic and instance segmentation, pixel retrieval requires a fine-grained recognition capability for variable-granularity targets. To this end, we propose pixel retrieval benchmarks named PROxford and PRParis, which are based on the widely used image retrieval datasets, ROxford and RParis. Three professional annotators label 5,942 images with two rounds of double-checking and refinement. Furthermore, we conduct extensive experiments and analysis on the SOTA methods in image search, image matching, detection, segmentation, and dense matching using our pixel retrieval benchmarks. Results show that the pixel retrieval task is challenging to these approaches and distinctive from existing problems, suggesting that further research can advance the content-based pixel-retrieval and thus user search experience. The datasets can be downloaded from \href{https://github.com/anguoyuan/Pixel_retrieval-Segmented_instance_retrieval}{this link}.
With the attention gained by camera-only 3D object detection in autonomous driving, methods based on Bird-Eye-View (BEV) representation especially derived from the forward view transformation paradigm, i.e., lift-splat-shoot (LSS), have recently seen significant progress. The BEV representation formulated by the frustum based on depth distribution prediction is ideal for learning the road structure and scene layout from multi-view images. However, to retain computational efficiency, the compressed BEV representation such as in resolution and axis is inevitably weak in retaining the individual geometric details, undermining the methodological generality and applicability. With this in mind, to compensate for the missing details and utilize multi-view geometry constraints, we propose LSSInst, a two-stage object detector incorporating BEV and instance representations in tandem. The proposed detector exploits fine-grained pixel-level features that can be flexibly integrated into existing LSS-based BEV networks. Having said that, due to the inherent gap between two representation spaces, we design the instance adaptor for the BEV-to-instance semantic coherence rather than pass the proposal naively. Extensive experiments demonstrated that our proposed framework is of excellent generalization ability and performance, which boosts the performances of modern LSS-based BEV perception methods without bells and whistles and outperforms current LSS-based state-of-the-art works on the large-scale nuScenes benchmark.
Object Hallucination (OH) has been acknowledged as one of the major trustworthy challenges in Large Vision-Language Models (LVLMs). Recent advancements in Large Language Models (LLMs) indicate that internal states, such as hidden states, encode the "overall truthfulness" of generated responses. However, it remains under-explored how internal states in LVLMs function and whether they could serve as "per-token" hallucination indicators, which is essential for mitigating OH. In this paper, we first conduct an in-depth exploration of LVLM internal states in relation to OH issues and discover that (1) LVLM internal states are high-specificity per-token indicators of hallucination behaviors. Moreover, (2) different LVLMs encode universal patterns of hallucinations in common latent subspaces, indicating that there exist "generic truthful directions" shared by various LVLMs. Based on these discoveries, we propose Truthful-Guided Pre-Intervention (TruthPrInt) that first learns the truthful direction of LVLM decoding and then applies truthful-guided inference-time intervention during LVLM decoding. We further propose ComnHallu to enhance both cross-LVLM and cross-data hallucination detection transferability by constructing and aligning hallucination latent subspaces. We evaluate TruthPrInt in extensive experimental settings, including in-domain and out-of-domain scenarios, over popular LVLMs and OH benchmarks. Experimental results indicate that TruthPrInt significantly outperforms state-of-the-art methods. Codes will be available at https://github.com/jinhaoduan/TruthPrInt.
Few-Shot Learning is the challenge of training a model with only a small amount of data. Many solutions to this problem use meta-learning algorithms, i.e. algorithms that learn to learn. By sampling few-shot tasks from a larger dataset, we can teach these algorithms to solve new, unseen tasks. This document reports my work on meta-learning algorithms for Few-Shot Computer Vision. This work was done during my internship at Sicara, a French company building image recognition solutions for businesses. It contains: 1. an extensive review of the state-of-the-art in few-shot computer vision; 2. a benchmark of meta-learning algorithms for few-shot image classification; 3. the introduction to a novel meta-learning algorithm for few-shot object detection, which is still in development.
We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale object recognition by formulating the task of predicting the presence or absence of a specific action unit in a still image of a human face as holistic classification. We then explore the design space of our approach by considering both shared and independent representations for separate action units, and also different CNN architectures for combining color and motion information. We then move to the novel setup of the FERA 2017 Challenge, in which we propose a multi-view extension of our approach that operates by first predicting the viewpoint from which the video was taken, and then evaluating an ensemble of action unit detectors that were trained for that specific viewpoint. Our approach is holistic, efficient, and modular, since new action units can be easily included in the overall system. Our approach significantly outperforms the baseline of the FERA 2017 Challenge, with an absolute improvement of 14% on the F1-metric. Additionally, it compares favorably against the winner of the FERA 2017 challenge. Code source is available at https://github.com/BCV-Uniandes/AUNets.
Detection of colon polyps has become a trending topic in the intersecting fields of machine learning and gastrointestinal endoscopy. The focus has mainly been on per-frame classification. More recently, polyp segmentation has gained attention in the medical community. Segmentation has the advantage of being more accurate than per-frame classification or object detection as it can show the affected area in greater detail. For our contribution to the EndoCV 2021 segmentation challenge, we propose two separate approaches. First, a segmentation model named TriUNet composed of three separate UNet models. Second, we combine TriUNet with an ensemble of well-known segmentation models, namely UNet++, FPN, DeepLabv3, and DeepLabv3+, into a model called DivergentNets to produce more generalizable medical image segmentation masks. In addition, we propose a modified Dice loss that calculates loss only for a single class when performing multiclass segmentation, forcing the model to focus on what is most important. Overall, the proposed methods achieved the best average scores for each respective round in the challenge, with TriUNet being the winning model in Round I and DivergentNets being the winning model in Round II of the segmentation generalization challenge at EndoCV 2021. The implementation of our approach is made publicly available on GitHub.
Identifying relations between objects is central to understanding the scene. While several works have been proposed for relation modeling in the image domain, there have been many constraints in the video domain due to challenging dynamics of spatio-temporal interactions (e.g., between which objects are there an interaction? when do relations start and end?). To date, two representative methods have been proposed to tackle Video Visual Relation Detection (VidVRD): segment-based and window-based. We first point out limitations of these methods and propose a novel approach named Temporal Span Proposal Network (TSPN). TSPN tells what to look: it sparsifies relation search space by scoring relationness of object pair, i.e., measuring how probable a relation exist. TSPN tells when to look: it simultaneously predicts start-end timestamps (i.e., temporal spans) and categories of the all possible relations by utilizing full video context. These two designs enable a win-win scenario: it accelerates training by 2X or more than existing methods and achieves competitive performance on two VidVRD benchmarks (ImageNet-VidVDR and VidOR). Moreover, comprehensive ablative experiments demonstrate the effectiveness of our approach. Codes are available at https://github.com/sangminwoo/Temporal-Span-Proposal-Network-VidVRD.
Sensor fusion is a crucial augmentation technique for improving the accuracy and reliability of perception systems for automated vehicles under diverse driving conditions. However, adverse weather and low-light conditions remain challenging, where sensor performance degrades significantly, exposing vehicle safety to potential risks. Advanced sensors such as LiDARs can help mitigate the issue but with extremely high marginal costs. In this paper, we propose a novel transformer-based 3D object detection model "REDFormer" to tackle low visibility conditions, exploiting the power of a more practical and cost-effective solution by leveraging bird's-eye-view camera-radar fusion. Using the nuScenes dataset with multi-radar point clouds, weather information, and time-of-day data, our model outperforms state-of-the-art (SOTA) models on classification and detection accuracy. Finally, we provide extensive ablation studies of each model component on their contributions to address the above-mentioned challenges. Particularly, it is shown in the experiments that our model achieves a significant performance improvement over the baseline model in low-visibility scenarios, specifically exhibiting a 31.31% increase in rainy scenes and a 46.99% enhancement in nighttime scenes.The source code of this study is publicly available.
In recent years, number of edge computing devices and artificial intelligence applications on them have advanced excessively. In edge computing, decision making processes and computations are moved from servers to edge devices. Hence, cheap and low power devices are required. FPGAs are very low power, inclined to do parallel operations and deeply suitable devices for running Convolutional Neural Networks (CNN) which are the fundamental unit of an artificial intelligence application. Face detection on surveillance systems is the most expected application on the security market. In this work, TinyYolov3 architecture is redesigned and deployed for face detection. It is a CNN based object detection method and developed for embedded systems. PYNQ-Z2 is selected as a target board which has low-end Xilinx Zynq 7020 System-on-Chip (SoC) on it. Redesigned TinyYolov3 model is defined in numerous bit width precisions with Brevitas library which brings fundamental CNN layers and activations in integer quantized form. Then, the model is trained in a quantized structure with WiderFace dataset. In order to decrease latency and power consumption, onchip memory of the FPGA is configured as a storage of whole network parameters and the last activation function is modified as rescaled HardTanh instead of Sigmoid. Also, high degree of parallelism is applied to logical resources of the FPGA. The model is converted to an HLS based application with using FINN framework and FINN-HLS library which includes the layer definitions in C++. Later, the model is synthesized and deployed. CPU of the SoC is employed with multithreading mechanism and responsible for preprocessing, postprocessing and TCP/IP streaming operations. Consequently, 2.4 Watt total board power consumption, 18 Frames-Per-Second (FPS) throughput and 0.757 mAP accuracy rate on Easy category of the WiderFace are achieved with 4 bits precision model.
We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained visual understanding that is best described by natural language. We propose a unified model, and demonstrate how our end-to-end approach is more accurate and temporally coherent than a multi-stage pipeline combining state-of-the-art detection, tracking, and captioning models. Moreover, we propose a training strategy based on a mixture of disjoint tasks, which allows us to leverage diverse, large-scale datasets which supervise different parts of our model. Although each pretraining task only provides weak supervision, they are complementary and, when combined, result in noteworthy zero-shot ability and serve as strong initialization for additional finetuning to further improve accuracy. We carefully design new metrics capturing all components of our task, and show how we can repurpose existing video grounding datasets (e.g. VidSTG and VLN) for our new task. We show that our model improves upon a number of strong baselines for this new task. Furthermore, we can apply our model to the task of spatial grounding, outperforming prior state-of-the-art on VidSTG and VLN, without explicitly training for it. Code is available at https://github.com/google-research/scenic/tree/main/scenic/projects/densevoc.
Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists) very well due to the low-resolution voxelization and aggressive downsampling. To this end, we propose Sparse Point-Voxel Convolution (SPVConv), a lightweight 3D module that equips the vanilla Sparse Convolution with the high-resolution point-based branch. With negligible overhead, this point-based branch is able to preserve the fine details even from large outdoor scenes. To explore the spectrum of efficient 3D models, we first define a flexible architecture design space based on SPVConv, and we then present 3D Neural Architecture Search (3D-NAS) to search the optimal network architecture over this diverse design space efficiently and effectively. Experimental results validate that the resulting SPVNAS model is fast and accurate: it outperforms the state-of-the-art MinkowskiNet by 3.3%, ranking 1st on the competitive SemanticKITTI leaderboard. It also achieves 8x computation reduction and 3x measured speedup over MinkowskiNet with higher accuracy. Finally, we transfer our method to 3D object detection, and it achieves consistent improvements over the one-stage detection baseline on KITTI.